Monday, November 23, 2015

Alibaba, Flipkart, Snapdeal and Amazon using analytics for fraud detection

Analytics and advanced algorithms are helping e-commerce companies to battle online fraud. The nature of fraud keeps on changing and also become complex as various players become mature. Analytics have to be used constantly by these firms have to scan huge amount of transactional and master data to draw inferences out of them. The fraudulent transactions can be not only from the customers but also from various other players like sellers who use these market place. Various parameters are used in these algorithms to scan and ween out fraudsters. For example product pricing or discounts, consumer complaints can be an indicator if the seller is selling fake products. Fraud detection has become an area of competitive advantage for e-commerce companies like Alibaba, Flipkart, Snapdeal and Amazon. 

Monday, November 9, 2015

India will have the largest global workforce by 2050

India will overtake China with 18.8 percent of global workforce compared to China’s share of 13 % by the year 2050 according to Bloomberg. These projection are made on the basis of the projection of the working age population. This could be a key asset for India as the India grows economically. However there are few challenges like skill and jobs for a large population that needs to be overcome.  

Friday, October 16, 2015

ANALLYZ :Self-Service Analytics

ANALLYZ is a Free, Cloud-based, Interactive, Self-service Business Analytics Software. It has been developed with a vision to provide an easy tool to Business Users, which they can leverage for Business Analytics, without relying on Statisticians or Data Scientists. It allows one to do whole gamut of Analytics work, ranging from Data Visualization, Simple Queries, Predictive Analytics, Optimization, Time-series Analysis to Text Mining. For the uninitiated, there is Self-driven Training on Statistics and Analytics techniques. For Business Users, looking for something specific, there are Tools for Supply Chain, Finance, Simulation, Operations etc. Click on the  links below to explore Self-service Tools on Predictive Analytics, Text Mining, Training and some specific Business applications like Demand Forecasting, Safety Stock Analysis, Text Analytics, Simulation, Markov Chain Analysis etc.
Please let us know what do you feel about : Self-Service Analytics by taking a small survey.

Wednesday, October 7, 2015

Graphical Techniques: In Analytics

Graphical Techniques: In Analytics
 Primarily Line, Table, Column, Bar, Pie, Scatter Chart, Histogram etc. are used.
Categorical Data: The only measure which could be used on them is counts for each Categories. Accordingly, we can use Table, Bar(Column) or Pie Chart for them.
Continuous Data: The most widely used techniques are Histogram (also called Frequency Distribution) and Line Charts (mostly used with data stamped with Time).
Please load Sample data set Country_Car_Sales on Training Page and use Descriptive Statistics option to learn different techniques.
Example: Read variables AnnualCarSales, GDP, SizeofEconomy etc. to generate different charts. Depending on whether the selected variable is Continuous or Categorical, appropriate charts are generated. 
Combination: We often encounter a mix of Categorical and Continuous data, which in Analytics parlance are also called Dimension andMeasure respectively.
When we combine two Dimensions we get what is known as a Contingency Table. We can combine two continuous variables by a Scatter plot. We can combine Categorical and Continuous data by aggregating Continuous values for Categories by means of Bar or Column Charts.
Line/Column/Bar Chart
 Line, Bar etc. can be used to see distribution of a Measure for a particular Dimension. The measure can be either a sum or mean for a Category. 
 Scatter/Bubble Plot: Scatter Plot is used to find relationship (correlation) between two Continuous(numeric) variables. It can be an important insight for detailed Analysis like Variable Screening or Predictive Modelling. Bubble Plots are advanced Scatter Plots which use an additional Size variable. It can accomodate an ID variable too, which has to be a Categorical(Dimension) Variable.

Monday, September 21, 2015

Anallyz Self Service BI and Analytics - Intro Analytics

Anallyz Self Service BI and Analytics - Intro Analytics
Out of several definitions, which can be used for Analytics, the following should suffice for most of the cases. "ANALYTICS means set of techniques, which gives STRUCTURE to large amount of INFORMATION for actionable INSIGHTS." Structure by Charts, Graphs, Aggregations, Groupings, Inferences, Combinations, Trends etc. Insights by showing What happened, Why it happened, What can happen and What should be done for that.
 Ingredients of Analytics
We will focus on STATISTCS and SMART SOFTWARE (Machine Learning), and mention other ingredients wherever appropriate.
Analytics relies heavily on Classical Statistics and Smart Software, sometimes used independently and sometimes in a combined fashion.
 STATISTICS can be classified into Descriptive and Inferential Statistics. Descriptive Statistics presents summarized view of the as-it-is data, which is easier to use and interpret. Descriptive can be further classified into Graphical and Numerical Statistics. Inferential Statistics mainly refers to techniques, by which we deduce a measure about data(population), based on a part of it(sample) drawn from it. Before we proceed, let us arm ourselves with basic understanding of some concepts.
 Population: Population consists of all the items of interest, which can be possibly used for Analytics. Example could be all adults eligible for voting in a country,all cars plying on the road in a city or all gears manufactured at a plant.
 Sample: We could possibly use all items in a population, however we seldom do that due to huge cost and time involved with it. What we normally do is to take a part of the Population. But we refrain from picking people from the same city or gears manufactured in a single week. We would pick every nth person(Simple Random Sample) from a city, from different age groups(Stratified Sample) in a city and do the same for multiple Cities(Cluster Sample).

Variable is a characteristic of the Population or the Sample. As an example Vote preferences or Weights of people could be a variable. As the name suggests, it can take several values.
 Data is the measured or observed value of a variable. When the data can take uncountable number of values, it is called Continuous Data (Interval, Quantitative Data). When the data can take only finite, countable number of values, it is called Categorical (Discrete, Nominal or Qualitative Data). When we measure weight of a person in absolute value, say lbs. it is Continuous. But when we put him in any of the three categories (Obese, Normal, Under-weight), it is Categorical.
Observe the alignment of Analytics Objectives and Techniques below. We are going to learn Descriptive and Inferential Stastics as foundation for more advanced concepts.

Friday, September 18, 2015

Everest Group had conducted a recent webinar on the market of analytics

Everest Group had conducted a recent webinar on the market of analytics:
  • Majority of analytics business process services are done in-house , meaning there is substantial opportunity for outsourcing
  • While the growth in analytics BPS last 3-4 years was 35-40% CAGR, projection (as per Everest estimates) for 2015-2018 CAGR are even higher at 40-45%
  • North America + EMEA account for 80-90% of the spend (North America 55-60%)
  • While majority of the current work is in reporting & descriptive analytics (both getting commoditized, productized, and automated gradually), there is increasing interest and growth in predictive and prescriptive analytics (both are more expertise based and less prone to commoditization)
  • Largest buyers are CPG & Retail (about 30%) and BFSI (about 25%) followed by Healthcare (about 10%) and High-tech & telecom (about 10%)
  • Revenue enhancement/top line growth is the primary driver of analytics spend
  • Almost all leading players get most revenues from North America

Tuesday, September 15, 2015

MoEngage received funding by Helion Ventures and Exfinity Ventures

MoEngage which is a mobile analytics firm has raised $4.25 million through a funding by Helion Ventures and Exfinity Ventures. They have also raised funds from Kunal Bahl and Rohit Bansal the founders of Snapdeal. MoEngage is building its mobile marketing automation platform which helps mobile based marketers to have focused marketing campaigns. It also helps app companies to work on personalized communications with users. 

Thursday, September 10, 2015

The TEACH Mission is Rotary's attempt to make India 100% literate by 2018

International Fellowship of Golfing Rotarians (IFGR) is conducting a "IFGR golf tournament" - details are available at the link below. Please register and invite your friends to this fantastic opportunity to enjoy the game and also help us raise funds for the "TEACH Mission".

Please register at the following link;

The TEACH Mission is Rotary's attempt to make India 100% literate by 2018. It includes use of E-learning techniques, Adult education, Teacher's Training, Providing  essentials to school children, and equipping schools with necessary infrastructure for imparting quality education. Coming close on the heels of our stupendous success in finally getting India off the Polio map through our decades long Global Polio eradication programme, we believe that this goal is achievable as well. Please share this information with all of your friends and acquaintances and help us make India better.

Monday, September 7, 2015

Fundamentals of Safety Stock

Before we get into the calculations of safety stock we need to understand on why do we need safety stock?  The need for safety stock is primarily to cater to the variations in supply and demand. If there was no uncertainty in demand or supply then there would be no need in safety stock. Since we are dealing with uncertainty and variation the obvious way to calculate safety stock would be using the standard deviation for the variation in demand and supply.
The other important concept that need to be understood while calculating safety stock is the service level. Service level is the percentage of demand that needs to be met from the on hand inventory level.
Service level: It is measured in two ways.
Fill Rate and Probability of Stock Out.
Fill Rate: If there were 3 orders in a week. Each order was of 100 units, which means the total demand was 300 units. The first and the second order was met in full while the last order only 20 units could be supplied then the fill rate would be 210/300 = 70%.
Probability of Stock Out: It is the number of orders that were met in full in a particular period from the inventory on hand. For example if in a particular week there were 3 orders and only 2 could be met in full then the Probability of Stock Out is 2/3 = 67%
 The other factors that need to be considered are Lead Time, Forecast and Forecast Period, Order Cycle, Reorder point, Lead Time Demand etc. Safety stock formulas are often changed based on individual customer requirements.
Mathematically the relationship between safety stock, Reorder point and the Lead Time demand is given as Reorder point = Safety Stock + Reorder Point