Subscribe to our Newsletter | To Post On IoT Central, Click here


analytics (15)

Today we are into digital age, every business is using big data and machine learning to effectively target users with messaging in a language they really understand and push offers, deals and ads that appeal to them across a range of channels.
With exponential growth in data from people and & internet of things, a key to survival is to use machine learning & make that data more meaningful, more relevant to enrich customer experience.
Machine Learning can also wreak havoc on a business if improperly implemented. Before embracing this technology, enterprises should be aware of the ways machine learning can fall flat.Data scientists have to take extreme care while developing these machine learning models so that it generate right insights to be consumed by business.
Here are 5 ways to improve the accuracy & predictive ability of machine learning model and ensure it produces better results.
·       Ensure that you have variety of data that covers almost all the scenarios and not biased to any situation. There was a news in early pokemon go days that it was showing only white neighborhoods. It’s because the creators of the algorithms failed to provide a diverse training set, and didn't spend time in these neighborhoods. Instead of working on a limited data, ask for more data. That will improve the accuracy of the model.
·       Several times the data received has missing values. Data scientists have to treat outliers and missing values properly to increase the accuracy. There are multiple methods to do that – impute mean, median or mode values in case of continuous variables and for categorical variables use a class. For outliers either delete them or perform some transformations.
·       Finding the right variables or features which will have maximum impact on the outcome is one of the key aspect. This will come from better domain knowledge, visualizations. It’s imperative to consider as many relevant variables and potential outcomes as possible prior to deploying a machine learning algorithm.
·       Ensemble models is combining multiple models to improve the accuracy using bagging, boosting. This ensembling can improve the predictive performance more than any single model. Random forests are used many times for ensembling.
·       Re-validate the model at proper time frequency. It is necessary to score the model with new data every day, every week or month based on changes in the data. If required rebuild the models periodically with different techniques to challenge the model present in the production.
There are some more ways but the ones mentioned above are foundational steps to ensure model accuracy.
Machine learning gives the super power in the hands of organization but as mentioned in the Spider Man movie – “With great power comes the great responsibility” so use it properly.
Read more…

A to Z of Analytics

Analytics has taken world by storm & It it the powerhouse for all the digital transformation happening in every industry.

Today everybody is generating tons of data – we as consumers leaving digital footprints on social media,IoT generating millions of records from sensors, Mobile phones are used from morning till we sleep. All these variety of data formats are stored in Big Data platform. But only storing this data is not going to take us anywhere unless analytics is applied on it. Hence it is extremely important to close the loop with Analytics insights.
Here is my version of A to Z for Analytics:
Artificial Intelligence: AI is the capability of a machine to imitate intelligent human behavior. BMW, Tesla, Google are using AI for self-driving cars. AI should be used to solve real world tough problems like climate modeling to disease analysis and betterment of humanity.
Boosting and Bagging: it is the technique used to generate more accurate models by ensembling multiple models together
Crisp-DM: is the cross industry standard process for data mining.  It was developed by a consortium of companies like SPSS, Teradata, Daimler and NCR Corporation in 1997 to bring the order in developing analytics models. Major 6 steps involved are business understanding, data understanding, data preparation, modeling, evaluation and deployment.
Data preparation: In analytics deployments more than 60% time is spent on data preparation. As a normal rule is garbage in garbage out. Hence it is important to cleanse and normalize the data and make it available for consumption by model.
Ensembling: is the technique of combining two or more algorithms to get more robust predictions. It is like combining all the marks we obtain in exams to arrive at final overall score. Random Forest is one such example combining multiple decision trees.
Feature selection: Simply put this means selecting only those feature or variables from the data which really makes sense and remove non relevant variables. This uplifts the model accuracy.
Gini Coefficient: it is used to measure the predictive power of the model typically used in credit scoring tools to find out who will repay and who will default on a loan.
Histogram: This is a graphical representation of the distribution of a set of numeric data, usually a vertical bar graph used for exploratory analytics and data preparation step.
Independent Variable: is the variable that is changed or controlled in a scientific experiment to test the effects on the dependent variable like effect of increasing the price on Sales.
Jubatus: This is online Machine Learning Library covering Classification, Regression, Recommendation (Nearest Neighbor Search), Graph Mining, Anomaly Detection, Clustering
KNN: K nearest neighbor algorithm in Machine Learning used for classification problems based on distance or similarity between data points.
Lift Chart: These are widely used in campaign targeting problems, to determine which decile can we target customers for a specific campaign. Also, it tells you how much response you can expect from the new target base.
Model: There are more than 50+ modeling techniques like regressions, decision trees, SVM, GLM, Neural networks etc present in any technology platform like SAS Enterprise miner, IBM SPSS or R. They are broadly categorized under supervised and unsupervised methods into classification, clustering, association rules.
Neural Networks: These are typically organized in layers made up by nodes and mimic the learning like brain does. Today Deep Learning is emerging field based on deep neural networks.
 
Optimization: It the Use of simulations techniques to identify scenarios which will produce best results within available constraints e.g. Sale price optimization, identifying optimal Inventory for maximum fulfillment & avoid stock outs
PMML: this is xml base file format developed by data mining group to transfer models between various technology platforms and it stands for predictive model markup language.
Quartile: It is dividing the sorted output of model into 4 groups for further action.
R: Today every university and even corporates are using R for statistical model building. It is freely available and there are licensed versions like Microsoft R. more than 7000 packages are now available at disposal to data scientists.
Sentiment Analytics: Is the process of determining whether an information or service provided by business leads to positive, negative or neutral human feelings or opinions. All the consumer product companies are measuring the sentiments 24/7 and adjusting there marketing strategies.
Text Analytics: It is used to discover & extract meaningful patterns and relationships from the text collection from social media site such as Facebook, Twitter, Linked-in, Blogs, Call center scripts.
Unsupervised Learning: These are algorithms where there is only input data and expected to find some patterns. Clustering & Association algorithms like k-menas & apriori are best examples.
Visualization: It is the method of enhanced exploratory data analysis & showing output of modeling results with highly interactive statistical graphics. Any model output has to be presented to senior management in most compelling way. Tableau, Qlikview, Spotfire are leading visualization tools.
What-If analysis: It is the method to simulate various business scenarios questions like what if we increased our marketing budget by 20%, what will be impact on sales? Monte Carlo simulation is very popular.
What do think should come for X, Y, Z?
Read more…
Internet of Things (IoT) began as an emerging trend and has now become one of the key element ofDigital Transformationthat is driving the world in many respects.
If your thermostat or refrigerator is connected to the Internet, then it is part of the consumer IoT.  If your factory equipment have sensors connected to internet, then it is part of Industrial IoT(IIoT).
IoT has an impact on end consumers, while IIoT has an impact on industries like Manufacturing, Aviation, Utility, Agriculture, Oil & Gas, Transportation, Energy and Healthcare.
IoT refers to the use of "smart" objects, which are everyday things from cars and home appliances to athletic shoes and light switches that can connect to the Internet, transmitting and receiving data and connecting the physical world to the digital world.
IoT is mostly about human interaction with objects. Devices can alert users when certain events or situations occur or monitor activities:
·       Google Nest sends an alert when temperature in the house dropped below 68 degrees
·       Garage door sensors alert when open
·       Turn up the heat and turn on the driveway lights a half hour before you arrive at your home
·       Meeting room that turns off lights when no one is using it
·       A/C switch off when windows are open
IIoT on the other hand, focus more workers safety, productivity & monitors activities and conditions with remote control functions ability:
·       Drones to monitor oil pipelines
·       Sensors to monitor Chemical factories, drilling equipment, excavators, earth movers
·       Tractors and sprayers in agriculture
·       Smart cities might be a mix of commercial and IIoT.
IoT is important but not critical while IIoT failure often results in life-threatening or other emergency situations.
IIoT provides an unprecedented level of visibility throughout the supply chain. Individual items, cases, pallets, containers and vehicles can be equipped with auto identification tags and tied to GPS-enabled connections to continuously update location and movement.
IoT generates medium or high volume of data while IIoT generates very huge amounts of data (A single turbine compressor blade can generate more than 500GB of data per day) so includes Big Data,Cloud computingmachine learning as necessary computing requirements.
In future, IoT will continue to enhance our lives as consumers while IIoT will enable efficient management of entire supply chain.
Read more…
How many times you have listened to the advice of your friend/colleague or someone you know, to invest in stock market? Many people have gained and lost their fortune with this guess work and now younger generation is more scared to hand over their hard earned money to someone for investing.
Until recently, you had 2 options for investments - either hire a human financial advisor or do it yourself. Human advisors charge substantial fees starting minimum 1% of value of assets to manage your portfolios. Do it yourself option requires lot of time and energy and you may lose your money due to result of overtrading, panic-selling during downturns, and trying to time the market as the issue for many individuals is they aren’t cut out to go it alone
This is where robo-advisors have scored more over humans.
A robo-advisor is an online, automated wealth management service based on data science algorithms with no or minimal human interventions that allocate, deploy and rebalance(spreading your money in stocks, mutual funds, bonds to balance risks) your investments.
The robo-advisor industry is in its infancy. Online life is migrating from persona desktop computing to laptops to tablets and finally to mobile.
Here are some of the advantages of using a robo-advisor:
·       Cheaper fees or free compared to traditional financial advisors
·       Automatic diversification into various options
·       Easy online access as we all are accustomed to shiny apps on mobile
·       Safer than picking your own stocks
·       You don’t need a degree in finance to understand the recommendations.
Big data and advanced analytics can help broaden the scope of robo-advice dramatically, incorporating financial planning into broader retirement planning, tax planning, vacation savings, higher education planning.
Robo-Advisors have typically targeted millennials segment because these young investors want to save & multiple money faster and often don't have enough patience & wealth to warrant the attention and interest of a human advisor.
High Net worth Individuals also think, online and automated investment tools can positively affect their wealth manager's advice and decision-making.
Overall, robo-advisors provide a good user experience with latest digital technologies such as slick apps and fancy interfaces. These platforms make sure that they fit right in with your daily online browsing,  and are great options for novice investors who are just starting out and want to dip their toes in the world of investments, or for people with a simple financial plan who just need an affordable, straightforward place to start their retirement plans
Wealthfront & Betterment are two popular commercial fee based robo-advisors available today. In the Free category WiseBanyan & CharlesSchwab are making the ground.
But it won’t be long before Amazon, Google, Facebook and Apple get in on the robo-advisor industry.
Robo advice is certainly here to stay, and it has its place in the wealth management landscape of tomorrow. But what's missing most, with robo-advisers is the personal touch.  In this age of hyper-personalization, the lack of a human element is one area where robo-advisors may fall short.
The robo-advisor can't replace a trusted age old adviser, your elders have worked with, who lives nearby and can rush right over in case of need, who knows you and your family.

With the pace of improvement that Artificial Intelligence and machine learning bringing up, robo-advice has the potential to become highly personalized and specific over time.
Read more…
Today, with Digitization of everything, 80 percent the data being created is unstructured. 
Audio, Video, our social footprints, the data generated from conversations between customer service reps, tons of legal document’s texts processed in financial sectors are examples of unstructured data stored in Big Data.
Organizations are turning to natural language processing (NLP) technology to derive understanding from the myriad of these unstructured data available online and in call-logs.
Natural language processing (NLP) is the ability of computers to understand human speech as it is spoken. NLP is a branch of artificial intelligence that has many important implications on the ways that computers and humans interact. Machine Learning has helped computers parse the ambiguity of human language.
Apache OpenNLP, Natural Language Toolkit(NLTK), Stanford NLP are various open source NLP libraries used in real world application below.
Here are multiple ways NLP is used today:
The most basic and well known application of NLP is Microsoft Word spell checking.
Text analysis, also known as sentiment analytics is a key use of NLP. Businesses are most concerned with comprehending how their customers feel emotionally adn use that data for betterment of their service.
Email filters are another important application of NLP. By analyzing the emails that flow through the servers, email providers can calculate the likelihood that an email is spam based its content by using Bayesian or Naive based spam filtering.
Call centers representatives engage with customers to hear list of specific complaints and problems. Mining this data for sentiment can lead to incredibly actionable intelligence that can be applied to product placement, messaging, design, or a range of other use cases.
Google and Bing and other search systems use NLP to extract terms from text to populate their indexes and to parse search queries.
Google Translate applies machine translation technologies in not only translating words, but in understanding the meaning of sentences to provide a true translation.
Many important decisions in financial markets use NLP by taking plain text announcements, and extracting the relevant info in a format that can be factored into algorithmic trading decisions. E.g. news of a merger between companies can have a big impact on trading decisions, and the speed at which the particulars of the merger, players, prices, who acquires who, can be incorporated into a trading algorithm can have profit implications in the millions of dollars.
Since the invention of the typewriter, the keyboard has been the king of human-computer interface. But today with voice recognition via virtual assistants, like Amazon’s Alexa, Google’s Now, Apple’s Siri and Microsoft’s Cortana respond to vocal prompts and do everything from finding a coffee shop to getting directions to our office and also tasks like turning on the lights in home, switching the heat on etc. depending on how digitized and wired-up our life is.
Question Answering - IBM Watson is the most prominent example of question answering via information retrieval that helps guide in various areas like healthcare, weather, insurance etc.
Therefore it is clear that Natural Language Processing takes a very important role in new machine human interfaces. It’s an essential tool for leading-edge analytics & is the near future.
Read more…

This is how Analytics is changing the game of Sports!!

Analytics and Big Data have disrupted many industries, and now they are on the edge of scoring major points in sports. Over the past few years, the world of sports has experienced an explosion in the use of analytics
Till few years back experience, gut feelings, and superstition have traditionally shaped the decision making process in sports.
It is first started with Oakland Athletics' General Manager, Billy Beane, who applied analytics for selecting right players. This was the first known use of statistics and data to make decisions in professional sports.
Today, every major professional sports team either has an analytics department or an analytics expert on staff.  From coaches and players to front offices and businesses, analytics can make a difference in scoring touchdowns, signing contracts or preventing injuries.
Big name organizations such as the Chicago Cubs, and Golden State Warriors are realizing that this is the future of sports and it is in their best interest to ride the wave while everyone else is trying to learn how to surf.
Golden State Warriors, have similarly used big data sets to help owners and coaches recruit players and execute game plans.
SportVu has six cameras installed in the NBA arenas to track the movements of every player on the court and the basketball 25 times per second. The data collected provides a plethora of innovative statistics based on speed, distance, player separation and ball possession to improve next games.
Adidas miCoach app works by having players attach a wearable device to their jerseys. Data from the device shows the coach who the top performers are and who needs rest. It also provides real-time stats on each player, such as speed, heart rate and acceleration.
Patriots developed a mobile app called Patriots Game Day Live, available to anyone attending a game at Gillette Stadium. With this app, they are trying to predict the wants and needs of fans, special content to be delivered, in-seat concession ordering and bathroom wait times.
FiveThirtyEight.com, provides details into more than just baseball coverage. It has over 20 journalists crunching numbers for fans to gain a better understanding of an upcoming game, series or season.
Motus’ new sleeves for tracking a pitcher’s throwing motion, measuring arm stress, speed and shoulder rotation. The advanced data generated from this increases a player’s health, performance and career. Experts can now predict with greater confidence if and when a pitcher with a certain throwing style will get injured.

In the recent Cricket world cup, every team had its own team of Data Analysts. They used various technologies like Cloud Platform and visualizations to predict scores, player performance, player profiles and more. Around 40 years’ worth of Cricket World Cup data is being mined to produce insights that enhances the viewer's experience. 
Analytics can advance the sports fans' experience as teams and ticket vendors compete with the at-home experience -- the better they know their fans, the better they can cater to them.
This collection of data is also used for internet ads, which can help with the expansion and growth of your organization through social media platforms or websites. 
  • What would be the most profitable food served at the concession stand?
  • What would be the best prices to sell game day tickets?
  • Determine which player on the team is the most productive?
  • Which players in the draft will become all-stars, and which ones will be considered role players?
  • Understand the fans behavior at the stadium via their app and push relevant information accordingly.
In this Digital age, Analytics are the present and future of professional sports. Any team that does not apply them to the fullest is at a competitive disadvantage.
Read more…

Do you know what is powerful real-time analytics?

In the Digital age today, world has become smaller and faster. 
Global audio & video calls which were available only in corporate offices, are now available to common man on the smartphone.
Consumers have more information of the products and comparison than the manufactures at any time, any place, and any device.
Gone are the days, when organizations used to load data in their data warehouse overnight and take decision based on BI, next day. Today organizations need actionable insights faster than ever before to stay competitive, reduce risks, meet customer expectations, and capitalize on time-sensitive opportunities – Real-time, near real-time.
Real-time is often defined in microseconds, milliseconds, or seconds, while near real-time in seconds, minutes.
With real-time analytics, the main goal is to solve problems quickly as they happen, or even better, before they happen. Real-time recommendations create a hyper-personal shopping experience for each and every customer.
The Internet of Things (IoT) is revolutionizing real-time analytics. Now, with sensor devices and the data streams they generate, companies have more insight into their assets than ever before.
Several industries are using this streaming data & putting real-time analytics. 
·        Churn prediction in Telecom
·        Intelligent traffic management in smart cities
·        Real-time surveillance analytics to reduce crime
·        Impact of weather and other external factors on stock markets to take trading decisions
·        Real-time staff optimization in Hospitals based on patients 
·        Energy generation and distribution based on smart grids
·        Credit scoring and fraud detection in financial & medical sector
Here are some real world examples of real-time analytics:
·        City of Chicago collects data from 911 calls, bus & train locations, 311 complaint calls & tweets to create a real-time geospatial map to cut crimes and respond to emergencies
·        The New York Times pays attention to their reader behavior using real-time analytics so they know what’s being read at any time. This helps them decide which position a story is placed and for how long it’s placed there
·        Telefonica the largest telecommunications company in Spain can now make split-second recommendations to television viewers and can create audience segments for new campaigns in real-time
·        Invoca, the call intelligence company, is embedding IBM Watson cognitive computing technology into its Voice Marketing Cloud to help marketers analyze and act on voice data in real-time.
·        Verizon now enables artificial intelligence and machine learning, predicting the customer intent by mining unstructured data and correlations
·        Ferrari, Honda & Red Bull use data generated by over 100 sensors in their Formula 
One cars and apply real-time analytics, giving drivers and their crews the information they need to make better decisions about pit stops, tire pressures, speed adjustments and fuel efficiency.
Real-Time analytics helps getting the right products in front of the people looking for them, or offering the right promotions to the people most likely to buy. For gaming companies, it helps in understanding which types of individuals are playing which game, and crafting an individualized approach to reach them.
As the pace of data generation and the value of analytics accelerate, real-time analytics is the top most choice to ride on this tsunami of information.
More and more tools such as Cloudera Impala, AWS, Spark, Storm, offer the possibility of real-time processing of Big Data and provide analytics,

Now is the time to move beyond just collecting, storing & managing the data to take rapid actions on the continuous streaming data – Real-Time!! 

Read more…

Digital Transformation in Utilities sector

It is easy to take for granted the technology we have at our disposal. We flick a switch and the lights go on, we turn on the tap and clean water comes out. We don’t have to worry about gas for cooking. 
But today the Utilities industry is under pressure to simultaneously reduce costs and improve operational performance.
Utilities sector is a bit late in digital innovations than RetailBanking or Insurance. With energy getting on the digital bandwagon with online customer engagement, smart sensors and better use of analytics, Utilities are now adopting it.
Digital technology gives utility companies the opportunity to collect much richer, customer level data, analyze it for service improvements, and add new services to change the way customers buy their products.
Smart technology will be used to monitor home energy usage, to trigger alerts when previously established maximum limits are being reached, and to offer ‘time of use’ tariffs that reward consumers for shifting demand from peak times. 
Electricity is the most versatile and widely used form of energy and global demand is growing continuously. Smart grids manage the electricity demand in sustainable, reliable and economic manner.
Advantages of Digital Transformation:
  • Digital makes customer self-service easy.
  • Digitally engaged customers trust their utilities.
  • Customer care, provided through digital technology, offers utilities both cost-to-serve efficiencies and improved customer intimacy.
  • Digital technology brings the capability to provide more accurate billing and payment processing, as well as faster response times for changing addresses and bills, removing and adding services, and many other functions
  • Using Mobile as a primary customer engagement channel for tips and alerts
  • Predictive maintenance with outage maps and real time alerts to service engineer helps reduce the downtime and costs
  • Smart meters allows utilities organizations to inform their customers about the energy consumption, tailor products and services to their customers while   achieving significant operational efficiencies at the same time

Meridian, a New Zealand energy company, launched PowerShop, an online energy retail market place that gives customers choice and control over how much power they buy and use. This helped Meridian attract online consumers and extend its reach of core retail offering.
Google’s Nest, an IoT enabled energy efficiency management gives details about consumption patterns and better control.
Thames Water, UK’s largest provider of water uses digital for remote asset monitoring to anticipate equipment failures and respond in near real time.
Big Data analytics and actionable intelligence gives competitive advantage by gained efficiency. 
IBM Watson with its cognitive computing power helped utilities identify trend and pattern analysis, predict which assets or pieces of equipment are most likely to cause points of failure. 
Today more than ever, utilities companies are asking: “How can we be competitive in this digital world?” People, whether they are customers, citizens or employees, increasingly expect a simple, fast and seamless experience. 
Read more…

Product recommendations in Digital Age

By 1994 the web has come to our doors bringing the power of online world at our doorsteps. Suddenly there was a way to buy things directly and efficiently online.
Then came eBay and Amazon in 1995....... Amazon started as bookstore and eBay as marketplace for sale of goods.
Since then, as Digital tsunami flooded, there are tons of websites selling everything on web but these two are still going great because of their product recommendations.
We as customers, love that personal touch and feeling special, whether it’s being greeted by name when we walk into the store, a shop owner remembering our birthday, helping us personally to bays where products are kept, or being able to customize a website to our needs. It can make us feel like we are single most important customer. But in an online world, there is no Bob or Sandra to guide you through the product you may like. This is where recommendation engines do a fantastic job.
With personalized product recommendations, you can suggest highly relevant products to your customers at multiple touch points of the shopping process. Intuitive recommendations will make every customer feel like your shop was created just for them.
Product recommendation engines can be implemented by collaborative filtering, content-
based filtering, or with the use of hybrid recommender systems.
There are various types of product recommendations:
           ·        Customers who bought this also bought - like Amazon
           ·        Best sellers in store – like HomeDepot
           ·        Latest products or arriving soon – like GAP
           ·        Items usually bought together – like Amazon
           ·        Recently views based on history – like Asos
           ·        Also buy at checkout – like Lego
There are many benefits that a product recommendation engine can do for digital marketing and it can go a long way in making your customers love your website and making it their favorite eCommerce site to shop for.
Advantages of product recommendations:
·        Increased conversion rate
·        Increased order value due to cross-sell
·        Better customer loyalty
·        Increased customer retention rates
·        Improved customer experience
Application of Data Science to analyze the behavior of customers to make predictions about what future customers will like. Big Data along with machine learning and artificial intelligence are the key to product recommendations.
Understanding the shopper’s behavior on different channels is also a must in personalizing the experience. Physical retail, mobile, desktop and e-mails are the main sources of information for the personalization engines
Amazon was the first player in eCommerce to invest heavily on product recommendations. Its recommendation system is based on a number of simple elements: what a user has bought in the past, which items they have in their virtual shopping cart, items they’ve rated and liked, and what other customers have viewed and purchased. Amazon has used this algorithm to customize the browsing experience & pull returning customers. This has increased their sale by over 30%.
Yahoo, Netflix, Yahoo, YouTube, Tripadvisor, and Spotify are other famous sites taking advantage of the recommender systems. Netflix ran a famous 1 million dollars competition from 2006 till 2009 to improve their recommendation engine.
Many commercial product recommendation engines are available today such as Monetate, SoftCube, Barilliance, Strands etc.
Ultimately most important goal for any eCommerce platform is to convert visitors into paying customers. Today the customer segmentation era as gone and its hyper- personalization
Product recommendations are extremely important in digital age !!
Read more…

Using Data Science for Predictive Maintenance

Remember few years ago there were two recall announcements from National Highway Traffic Safety Administration for GM & Tesla – both related to problems that could cause fires. These caused tons of money to resolve.
Aerospace, Rail industry, Equipment manufacturers and Auto makers often face this challenge of ensuring maximum availability of critical assembly line systems, keeping those assets in good working order, while simultaneously minimizing the cost of maintenance and time based or count based repairs.
Identification of root causes of faults and failures must also happen without the need for a lab or testing. As more vehicles/industrial equipment and assembly robots begin to communicate their current status to a central server, detection of faults becomes more easy and practical.
Early identification of these potential issues helps organizations deploy maintenance team more cost effectively and maximize parts/equipment up-time. All the critical factors that help to predict failure, may be deeply buried in structured data like equipment year, make, model, warranty details etc and unstructured data covering millions of log entries, sensor data, error messages, odometer reading, speed, engine temperature, engine torque, acceleration and repair & maintenance reports.
Predictive maintenance, a technique to predict when an in-service machine will fail so that maintenance can be planned in advance, encompasses failure prediction, failure diagnosis, failure type classification, and recommendation of maintenance actions after failure.
Business benefits of Data Science with predictive maintenance:
  • Minimize maintenance costs - Don’t waste money through over-cautious time bound maintenance. Only repair equipment when repairs are actually needed.
  • Reduce unplanned downtime - Implement predictive maintenance to predict future equipment malfunctioning and failures and minimize the risk for unplanned disasters putting your business at risk.
  • Root cause analysis - Find causes for equipment malfunctions and work with suppliers to switch-off reasons for high failure rates. Increase return on your assets.
  • Efficient labor planning — no time wasted replacing/fixing equipment that doesn’t need it
  • Avoid warranty cost for failure recovery – thousands of recalls in case of automakers while production loss in assembly line

TrainItalia has invested 50M euros in Internet of Things project which expects to cut maintenance costs by up to 130M euros to increase train availability and customer satisfaction.

Rolls Royce is teaming up with Microsoft for Azure cloud based streaming analytics for predicting engine failures and ensuring right maintenance.
Sudden machine failures can ruin the reputation of a business resulting in potential contract penalties, and lost revenue. Data Science can help in real time and before time to save all this trouble.
Read more…

Customer 360º view in Digital age

In today’s digital age of customer hyper-personalization, organizations identify opportunities for real time engagement based on data-driven understanding of customer behavior.
Customers have taken control of their purchase process. With websites, blogs, Facebook updates, online reviews and more, they use multiple sources of information to make decisions and often engage with a brand dozens of times between inspiration and purchase.
It’s important that organizations collect every customer interaction in order to identify sentiments of happy & unhappy customers.
Companies can get a complete 360º view of customers by aggregating data from the various touch points that a customer may use, to contact a company to purchase products and receive service/support.
This Customer 360º snapshot should include:
  • Identity: name, location, gender, age and other demographic data
  • Relationships: their influence, connections, associations with others
  • Current activity: orders, complaints, deliveries, returns
  • History: contacts, campaigns, processes, cases across all lines of business and channels
  • Value: which products or services they are associated with, including history
  • Flags: prompts to give context, e.g. churn propensity, up-sell options, fraud risk, mood of last interactions, complaint record, frequency of contact
  • Actions: expected, likely or essential steps based on who they are and the fact they are calling now

The 360º view of customers, also often requires a big data analytics strategy to marry structured data (data that can reside in the rows and columns of a database), with unstructured data (data like audio files, video files, social media data). 
Many companies like Nestle, Toyota are using social media listening tools to gather what customers are saying on sites like Facebook and Twitter, predictive analytics tools to determine what customers may research or purchase next.
What are the returns of Customer 360º:
  • All customer touch point data in a single repository for fast queries
  • Next best actions or recommendations for customers
  • All key metrics in a single location for business users to know and advise customers
  • Intuitive and customizable dashboards for quick insights
  • Real time hyper personalized customer interaction
  • Enhanced customer loyalty

Customer 360º helps achieve Single View of Customer across Channels – online, stores, marketplaces, Devices – wearables, mobile, tablets, laptops & Interactions – purchase, posts, likes, feedback, service.

This is further used for customer analytics – predict churn, retention, next best action, cross-sell & up-sell opportunities, profitability, life time value.
Global leaders in customer experience are Apple, Disney, Emirates.
A word of caution though - Focus & collect only that customer data, which can help to improve the customer journey.
Read more…

Why Data Science Is The Top Job In Digital Transformation

Digital Transformation has become a burning question for all the businesses and the foundation to ride on the wave is being data driven.
DJ Patil & Thomas Davenport mentioned in 2012 HBR article, that Data Scientist is the sexiest job of the century, and how true!  Even the latest Glassdoor ranked Data Scientist at 1st in top 25 best jobs in America.
Over the last decade there’s been a massive explosion in both the data generated and retained by companies. Uber, Airbnb, Netflix, Wallmart, Amazon, LinkedIn, Twitter all process tons of data every minute and use that for revenue growth, cost reductions and increase in customer satisfaction.
Most industries such as Retail, Banking, Travel, Financial Sector, Healthcare, and Manufacturing want to be able to make better decisions. With speed of change and profitability pressures on the businesses, the ability to take decisions had gone down to real time. Data has become an asset for every company, hence they need someone who can comb through these data sets and apply their logic and use tools to find some patterns and provide insights for future.
Think about Facebook, Twitter and other social media platforms,smartphone apps, in-store purchase behavior data, online website analytics, and now all connected devices with internet of things are generating tsunami of new data streams.
All this data is useless if not analyzed for actions or new insights.
The importance of Data Scientists has rose to top due to two key issues:
  • Increased need & desire among businesses to gain greater value from their data
  • Over 80% of data/information that businesses generate and collect is unstructured or semi-structured data that need special treatment 

Data Scientists:

  • Typically requires mix of skills - mathematics, statistics, computer science, machine learning and most importantly business knowledge
  • They need to employ the R or Python programming language to clean and remove irrelevant data
  • Create algorithms to solve the business problems
  • Finally effectively communicate the findings to management

Any company, in any industry, that crunches large volumes of numbers, possesses lots of operational and customer data, or can benefit from social media streams, credit data, consumer research or third-party data sets can benefit from having a data scientist or a data science team.

Top data scientists in the world today are:
  • Kirk D Borne of BoozAllen
  • D J Patil Chief Data Scientist at White House
  • Gregory Piatetsky of kdnuggets
  • Vincent Granville of Analyticsbridge
  • Jonathan Goldman of LinkedIn
  • Ronald Van Loon

Data science will involve all the aspects of statistics, machine leaning, and artificial intelligence, deep learning & cognitive computing with addition of storage from big data.

Read more…

Article: A Brief History of Field Programmable Devices (FPGAs)-data-analytics-alone-cannot-deliver-effective-automation-solutions-industrial-iot-min-jpg

By Akeel Al-Attar. This article first appeared here

Automated analytics (which can also be referred to as machine learning, deep learning etc.) are currently attracting the lion’s share of interest from investors, consultants, journalists and executives looking at technologies that can deliver the business opportunities being afforded by the Internet of Things. The reason for this surge in interest is that the IOT generates huge volumes of data from which analytics can discover patterns, anomalies and insights which can then be used to automate, improve and control business operations.


One of the main attractions of automated analytics appears to be the perception that it represents an automated process that is able to learn automatically from data without the need to do any programming of rules. Furthermore, it is perceived that the IOT will allow organisations to apply analytics to data being generated by any physical asset or business process and thereafter being able to use automated analytics to monitor asset performance, detect anomalies and generate problem resolution / trouble-shooting advice; all without any programming of rules!

In reality, automated analytics is a powerful technology for turning data into actionable insight / knowledge and thereby represents a key enabling technology for automation in Industrial IOT. However, automated analytics alone cannot deliver complete solutions for the following reasons:

i- In order for analytics to learn effectively it needs data that spans the spectrum of normal, sub normal and anomalous asset/process behaviour. Such data can become available relatively quickly in a scenario where there are tens or hundreds of thousands of similar assets (central heating boilers, mobile phones etc.). However, this is not the case for more complex equipment / plants / processes where the volume of available faults or anomalous behaviour data is simply not large enough to facilitate effective analytics learning/modelling. As a result any generated automated analytics will be very restricted in its scope and will generate a large number of anomalies representing operating conditions that do not exist in the data.

ii- By focussing on data analytics alone we are ignoring the most important asset of any organisation; namely the expertise of its people in how to operate plants / processes. This expertise covers condition / risk assessment, planning, configuration, diagnostics, trouble-shooting and other skills that can involve decision making tasks. Automating ‘Decision making’ and applying it to streaming real-time IOT data offers huge business benefits and is very complementary to automated analytics in that it addresses the very areas in point 1 above where data coverage is incomplete, but human expertise exists.

Capturing expertise into an automated decision making system does require the programming of rules and decisions but that need not be a lengthy or cumbersome in a modern rules/decision automation technology such as Xpertrule. Decision making tasks can be represented in a graphical way that a subject matter expert can easily author and maintain without the involvement of a programmer. This can be done using graphical and easy to edit decision flows, decision trees, decision tables and rules. From my experience in using this approach, a substantial decision making task of tens of decision trees can be captured and deployed within a few weeks.

Given the complementary nature of automated analytics and automated decisions, I would recommend the use of symbolic learning data analytics techniques. Symbolic analytics generate rules/tree structures from data which are interpretable and understandable to the domain experts. Whilst rules/tree analytics models are marginally less accurate than deep learning or other ‘blackbox models’, the transparency of symbolic data models offer a number of advantages:

i- The analytics models can be validated by the domain experts
ii- The domain experts can add additional decision knowledge to the analytics models
iii- The transparency of the data models gives the experts insights into the root causes of problems and highlights opportunities for performance improvement.

Combining automated knowledge from data analytics with automated decisions from domain experts can deliver a paradigm shift in the way organisations use IOT to manage their assets / processes. It allows organisations to deploy their best practice expertise 24/7 real time throughout the organisation and rapidly turn newly acquired data into new and improved knowledge.

Below are example decision and analytics knowledge from an industrial IOT solution that we developed for a major manufacturer of powder processing mills. The solution monitors the performance of the mills to diagnose problems and to detect anomalous behaviour:

The Fault diagnosis tree below is part of the knowledge captured from the subject matter experts within the company

Article: A Brief History of Field Programmable Devices (FPGAs)-fault-diagnosis-tree-min-jpg



The tree below is generated by automated data analytics and relates the output particle size to other process parameters and environmental variables. The tree is one of many analytics models used to monitor anomalous behaviour of the process.

Article: A Brief History of Field Programmable Devices (FPGAs)-automated-data-analytics-min-jpg



The above example demonstrates both the complementary nature of rules and analytics automation and the interpretability of symbolic analytics. In my next posting I will cover the subject of the rapid capture of decision making expertise using decision structuring and the induction of decision trees from decision examples provided by subject matter experts.

Read more…

Original article is published at Forbes: link

Have heard about the magic pill? Not sure how it works, but it helps you lose 20 pounds in a week while consuming the same calories as before. And you’ve probably also heard about the scary side effects of that pill. The need for magic pills is appearing in the IoT market as well. Thanks to the explosion of sensors to measure everything imaginable within the Internet of Things, enterprises are confronted with a never-ending buffet of tempting data.

Typically data has been consumed like food: first it is grown, harvested, and prepared. Then this enjoyable meal is ingested into a data warehouse and digested through analytics. Finally we extract the nutritional value and put it to work to improve some part of our operations. Enterprises have evolved to consume data from CRM, ERP, and even the Web that is high in signal nutrition in this genteel, managed manner from which they can project trends or derive useful BI.

sensory

The IoT and its superabundance of sensors completely changes that paradigm and we need to give serious consideration to our data dietary habits if we want to succeed in this new data food chain. Rather than being served nicely prepared data meals, sensor data is the equivalent of opening your mouth in front of some kind of cartoon food fire hose. Data comes in real-time, completely raw, and in such sustained volume that all you can do is keep stuffing it down.

And, as you would expect, your digestion will be compromised. You won’t benefit from that overload of raw IoT data. In fact, we’ll need to change our internal plumbing, our data pipelines, to get the full nutritional benefit of IoT sensor data.

That will require work, but if you can process the data and extract the value, that’s where the real power comes in.  In fact, you can attain something like superpowers. You can have the eyesight of eagles (self-driving cars), the sonar wave perception of dolphins (for detecting objects in the water), and the night vision of owls (for surveillance cameras).If we can digest all this sensor data and use it in creative ways, the potential is enormous. But how can we adapt to handle this sort of data? Doing so demands a new infrastructure with massive storage, real-time ingestion, and multi-genre analytics.

If we can digest all this sensor data and use it in creative ways, the potential is enormous. But how can we adapt to handle this sort of data? Doing so demands a new infrastructure with massive storage, real-time ingestion, and multi-genre analytics.

Massive storage. More than five years ago, Stephen Brobst predicted that the volume of sensor data would soon crush the amount of unstructured data generated by social media(remember when that seemed like a lot?). Sensor data demands extreme scalability.

Real-time ingestion. The infrastructure needs to be able to ingest raw data and determine moment by moment where to land it. Some data demands immediate reaction and should move into memory. Other data is needed in the data warehouse for operational reporting and analytics. Still other data will add benefit as part of a greater aggregation using Hadoop. Instant decisions will help parse where cloud resources are appropriate versus other assets.

Multi-genre analytics. When you have data that you’ve never seen before, you need to transform data and apply different types of algorithms. Some may require advanced analytics and some may just require a standard deviation. Multi-genre analytics allows you to apply multiple analytics models in various forms so that you can quickly discern the value of the data.

The self-driving car is a helpful metaphor. I’ve heard estimates that each vehicle has 60,000 sensors generating terabytes of data per hour. Consider the variety of that data. Data for obstacle detection requires millisecond response and must be recognized as such if it is to be useful. A sensor on the battery to predict replacement requires aggregation to predict a trend over time and does not require real-time responsiveness. Nevertheless both types of data are being created constantly and must be directed appropriately based on the use case.

How does this work at scale? Consider video games. Real-time data is critical to everything from in game advertising, which depends on near instant delivery of the right ad at a contextually appropriate moment, to recommendations and game features that are critical to the user experience and which are highly specific to moments within the game. At the same time, analyzing patterns at scale is critical to understanding and controlling churn and appeal. This is a lot of data to parse on the fly in order to operate effectively.

From a data perspective, we’re going to need a new digestive system if we are to make the most of the data coming in from the IoT. We’ll need vision and creativity as well. It’s an exciting time to be in analytics.

Read more…

Upcoming IoT Events

More IoT News

IoT Career Opportunities