Capstone projects

Capstone Project

A Case Study of Epilepsy Seizure Prediction
There is emerging evidence that the temporal dynamics of brain activity can be classified into 4 states: Interictal (between seizures, or baseline), Preictal (prior to seizure), Ictal (seizure), and Post-ictal (after seizures).READ MORE >

The Journey of Entry Level Data Scientists
The world of marching science and galloping technology demands tough decisions in life to stay special among the whole lot. That one special decision in life of aspiring.READ MORE >

Student Experience - Identifying Hidden Drug-Drug Interactions in FDA AERS  

ISB’s Certification Programme in Business Analytics’ experience bridged our fascination with analytics and our quest in solving real time problems by applying machine learning techniques.READ MORE >

A View of India Elections Past and Present Social and Historical - 2004 - 2014

This project presents an analysis of elections in India. It presents two views, past and present.
Present View: Social Media is being used extensively in the current elections by both parties and candidates. India has 103 million social media users of which a large proportion are the youth. Social Media sentiment analysis is a great way to understand the sentiment amongst the youth.The present view of the elections presents the social and media sentiment towards the major parties and candidates in the months of February and March prior to the start of the Elections.READ MORE>
 

A study of Insurance fraud using advanced analytics

The project offered by Polaris Financial Technology limited. Insurance fraud is the second biggest white-collar crimes in the U.S. after tax evasion, according to the National Insurance Crime Bureau.1 As insurers deal with an uncertain economic climate and intense competition, they must also grapple with the increasing incidence and sophistication of fraud, not to mention the resulting losses.READ MORE >
 

Identifying Trends through Social Media Analytics in Retail Space
With the advent of high-speed Internet and flourishing social media, today there is enormous textual data    available to    companies with respect to customer perception about products and services, how are competitors’ products doing  in the market, what is currently most happening which can be utilised etc. However, sensing all these sentiments from the textual data which comes in variety of forms is an important task.READ MORE >

Customer Profiling & Market Basket Analysis

A leading retailer chain wants to expand their chain of stores. To do this in the current competitive retail scenario, it is very crucial to know and understand the customers in order to create the right offers and schemes to retain and grow the existing customer base, reduce customer attrition and increase influx of new customers.READ MORE >

Econometric  data analysis for identifying locations to open new branches in India

We’re rapidly entering a world where everything can be monitored and measured,” said Erik Brynjolfsson, an economist and director of the Massachusetts Institute of Technology’s Center for Digital Business. “But the big problem is going to be the ability of humans to use, analyze and make sense of the data.”READ MORE >

Anomaly Detection Engine for Medical Technology Equipment

Monitoring of capital intensive health equipment is required (a) to reduce the equipment downtime, (b) increase the revenue generated from equipment usage, and (c) ensure the safety of operations as per regulations and auditory requirements. READ MORE >


Prediction of future security prices

Is it possible to predict future security prices based on historical data? Since the advent of the stock market, this question has been hotly debated by economists, investors and business professionals of all stripes. READ MORE > 

Fraud Analytics Using Machine-learning & Engineering on “Big Data” (FAME) for Telecom

Fraud Analytics Using Machine Learning & Engineering on Big Data (FAME) was one of its kind work done in Telecom Fraud Detection. The project was most exciting as it touched upon many unknown territories of data visualization, feature engineering, predictive model building and fine tuning, implementation on Big Data. READ MORE > 

Freight Optimization through Analytical Model

Client has large freight logistics network operating across various modes (i.e. rail, road, air, ship etc.). Client has its operations in around 2000 locations worldwide. One of the key for their operational success is movement of freight from one point to other in optimum time and cost.  READ MORE >