The Data Analysis vertical focuses to provide the critical link between good decision making and success. Analysis of data is a process of inspecting, cleaning, transforming, and modelling data with the goal of highlighting useful information, suggesting conclusions, and supporting decision making. Data analysis has multiple facets and approaches, encompassing diverse techniques under a variety of names, in different business, science, and social science domains. We provide business analysis on already available data and also collect data through various methods like surveys etc. Data analysis is basically used for for Prediction and Identification. We organize the rules of evidence for guiding the analysis by Falsifiability, Validity and Parsimony.

Why do we need statistical techniques?

Today’s competitive landscape makes the critical link between good decision making and success more important than ever.

From corporations and government organizations to research institutes and universities, increasingly organizations are turning to statistical analysis to guide decision-making processes.

Using optimal statistical techniques can provide new information that improves processes, drives development and revenues, and helps you retain valued and satisfied customers.

Statistics in Business and Life:

In real life, we use these techniques for a number of purposes like:

Predict the sales that a customer would contribute, given a certain set of attributes like demographic information, credit history, prior purchase behavior, etc.

Predict the probability of response from a direct mail thus saving cost and acquire potential customers.

Identify high responsive and high profit segments and targeting only these segments for direct mail campaigns

Prescriptive Analytics - What action should be taken?

Descriptive Analytics - What happened or is happening in the business?

Inquisitive Analytics - Why did it happen?

Predictive Analytics - What is likely to happen based on historical information?

We help our clients evolve through the various levels with which analytics can be deployed to solve business problems.

Sectors where Data Analysis can be applied:


Aggregate, rationalize, and manage your data

Get a single view of multiple data sources

Bring important patterns and trends into sharp relief

Use data strategically to improve outcomes, optimize performance, and understand insured populations

Significantly reduce costs by choosing to offshore data production

Optimize your service delivery

Identify new business opportunities


Analyzing the performance of a new store

Designing advertisements

Floor planning

Reporting and Sales Analysis

Predictive Analysis

Inventory Management

Promotion-Effectiveness Analysis

Demand Forecasting

Brand and Category Analysis

Vendor Analysis in terms of quality, time to supply etc.


Resource and Investment Optimization

Market Research Analysis

Spend Analysis

Capacity Planning

Banking and Insurance

Customer Segmentation

Customer Satisfaction Analysis

Market Measurement

Fraud Detection

Retention and Lapsation Analysis

Identifying Target Customers

Generating insights from various surveys

Analyzing performances of various departments e.g. Call Centre, Agencies

Reserve Adequacy

Yield Management

Technology, Media and Telecome

Customer Engagement Models

Web Analytics

Call Centre Analytics

Inventory Management

Customer Loyalty

Market Segmentation

Customer Segmentation

Design Optimization


Human Resource Department

Employees from which country/state perform better

Understanding employee characteristics

Population Analysis

Voting patterns of a particular region

Providing schemes like education schemes, public health schemes

Our Service Portfolio for the Data Analysis division includes the following :

Business Process Assessment & Optimization: Understand what's working, what's not and how to get the highest return on your investment

Financial Performance: "Follow the money" from claims submission to payment and recovery and plug the leaks that drown your bottom line

Data Warehousing: Manage your data effectively with data modeling, conversion, requirements analysis, analysis and reporting

Clinical Performance: Understand which treatments yield superior results and which need work

Member Analytics: Understand the populations you serve

Charge Analysis & Cost Diagnostic: Get to the bottom of your cost structure to understand where your money's going and if it's well spent

Predictive Modeling: See not just what's happening now, but what it will mean down the road

Fraud Detection & Prevention: Find and prevent fraudulent charges

Decision Support: Get the information you need to make the right choices

Custom Databases: Build the database that works for your organization

Designing Surveys: Design surveys to collect the correct information that helps in analyzing various aspects

Today’s competitive landscape makes the critical link between good decision making and success more important than ever… Ekklavya provides the Link!!

Medical Bill Process System

Ekklavya analyzed leading insurer’s medical bill processing system to unearth bottlenecks and reduce bill processing time


Client serves approximately 10K-12K medical bills per month
A medical bill undergoes various stages of processing prior to settlement
Client wanted to unearth bottlenecks in the medical bill resolution process to reduce the bill processing time
Our Solution

Exception handling and manual processing at Integrated System result in high cycle time
80% of bills handled through Exception Handling System churn only once. Only about 4-5% of the exceptions churn more than 3 times
January 2010 ‘Integrated System’ Recycle resulted in reduction of cycle time by ~50%

Complications / Requirements

Processing time was analyzed for various paths that a bill may take in its life-cycle

Detail analysis was done for the stages
   - Which handle exception bills (Exception
     Handling and Special Handling)
   - Manual processing

Pre and post comparative analysis to study the impact of January 2010 ‘Integrated System’ Recycle was done
Business Impact

The analysis was helpful in educating the providers at NY Claim office to change their claim data capturing process
Claims business used the analysis data points in discussions with external bill provider to revisit bill scanning
Claims business used the analysis to show Exception System that they spends lot of time on just 4-5 % of the exceptions

Price Optimization

Ekklavya’s Price Optimization framework helped the insurer increase profits


Client is auto insurer
- Retention has been declining over last 3 years
- New Business Close Rates have been falling

Direct distribution channel has grown rapidly but is performing poorly in terms of closing new business

The client wants to gain insights into
- Price Elasticity of shoppers
- Competitive Positioning
- Pricing strategies and scenarios
Our Solution

New pricing strategies can be configured and analyzed in 2-3 days reducing the cycle time by 80%
The flexible and modular optimization framework allows for maximum re-use of existing client assets
Optimize the entire portfolio for profit maximization
Complications / Requirements

Competitive Market Analysis to identify client’s quotes in ChoicePoint’s Shoppers database

Build multivariate statistical model for
- Price Elasticity
- Customer Retention
- Customer Life Time Value

Integrate Client’s Loss Model in the solution and customize the tool workbench for client specific requirements
Business Impact

The workbench enables business users to configure and analyze strategies without the need for writing code with immediate impact on analyst productivity
Post optimization, portfolio profits have gone up by 5.2% and the revenue by 6.8 %

Purchase Behavior

Help a Retailer Understand Purchase Behavior


The retailer who want to use syndicated research, consumer insights and sales history, to identify possible areas where they could improve sales of electronics. Direct distribution channel has grown rapidly but is performing poorly in terms of closing new business
The retailer’s large customer base can make it difficult to examine the entire population

Business Impact

Results of the analyses helped the retailer identify areas with the greatest headroom, better manage categories with strong demand and develop different offers that addressed the specific needs of each cluster

Using survey data, identify a representative cluster population Then scale internal sales, customer reported market share and market size
Then build a model that shows possible headroom at a product and cluster level
Insights from the model help to identify key improvement areas and understand key growth areas for each category

Segmenting Customers based on behavior

Helping Banks to develop a heterogeneous customer segments and identify potential revenue generators


Banks that want to develop a generic segmentation scheme that explains the overall variation in the population
Banks that want to identify homogeneous segments with respect to the profitability drivers and design specific products suited for different segments
Our Solution

The share of each segment based on revenue generating potential is :
- Low Tenure Inactive (34%)
- Thick File Dormants (17%)
- Auto Buyers (12%)
- Hit & Run (9%)
- Delinquents and Bankrupts (8%)

Delinquents and Bankrupts are youngest in both physical age and credit age while Dormants and Hit & Run segments constitute the eldest
Complications / Requirements

Segments were generated using Cluster analysis
Profile was based on various attributes such as tenure, profitability drivers, delinquency, bankruptcy
Nomenclature for segments based on profile characteristics and deviations from population metrics was done
Sales performance, revolving ratio, and response rates in various product campaigns in the past one year were compared to the population benchmark
Business Impact

Banks will be better able to target sales and marketing, this will lead to an increase in revenue
Net profit from the various segments improves

Reducing Silent Attrition

Helping Banks to develop a predictive model to reduce silent attrition


Any bank wanting to focus on balance retention in it’s checking and savings accounts can be benefitted
Banks that specifically want to enhance profitability by stemming the “silent attrition” (i.e. reduction of balance size over time which reduces account profitability)

Business Impact

The model can be used for providing preemptive alerts to allow proactive and timely action as a response
The “balance at risk” flag helps the bank decide which customers to prioritize
Based on test data, the estimated impact was a 14 to 18 percent reduction in silent attrition resulting in over 25 percent in incremental profits for this segment

A definition of silent attrition based on 6 month balance history was used to identify accounts with attrition
Historical and cross-sectional data was analyzed (using regression and CHAID), to profile the key drivers in these high risk customer groups
An index was created based on factors such as average balance amounts, checking card usage to identify “balance at risk” for each at-risk customer

Sales Force Plan of Action (POA) Development

Sales Force Plan of Action (POA) Development


Help companies design and implement a new call planning process that captures information flow starting from the raw data to the creation of inputs for the Customer Relationship Management (CRM) system

Business Impact

Optimizing data mart structure for efficient querying
Designing components as generic modules that were parameterized (to allow passing business rules as parameters) to accommodate most future rule changes
Creating standardized templates for input and output data to each module and adding quality control processes after each step

This process has to:

Be modular and flexible so that any changes to business rules could be implemented by changing the appropriate process modules
Be scalable such that any changes to the product portfolio and sales force structure could be easily accommodated within the framework