Big Data Research Associate
Institute for Development and Research in Banking Technology
Total years of experience :1 years, 4 Months
Research mainly in Text mining, Page rank and Machine learning algorithms like Neural networks, Support vector machine, Regression.
Using Big Data implementing new algorithms in Text mining.
Solving the Banking Business Usecases:
1) Churn Analysis
2) Market Basket Analysis (MBA)
3) RFM (Recency Frequency Monetory)
4) Scoring Rate
5) Sentiment Analysis
6) Text Mining
Data Analyst-Prodmetrics IT services (March 2013-Present)
• Manage data from many sources
• Identify & solve issues around data
• Interpret & present results and insights derived from the analysis
• Develop a data-driven analysis approach for clients.
• Serve as a subject matter expert for available data elements and analytics capabilities.
• Perform data mining investigations to find new insights related to customers and behavior.
• Coordinate with management and maintain reports
• Maintain records of contacts, accounts, and orders.
• Design, develop & perform data analysis and mining on various kinds & types data
Trained: Business Analytics and Big Data
Program: CPEE program from International School of Engineering.
Duration: 6months
Description: Predictive Analytics, Predictive Statistics, Optimization, Hadoop (BIG DATA)
My Professional Experience:
Predicting Number of Days in Hospital
Aim: Predicting Number of Days in Hospital data from the data Heritage Provider Network. The studies have concluded that in 2006 well over $30 billion was spent on unnecessary hospital admissions.
Dataset: 2668990 observations and 14 variables
Techniques: Decision Tree, Random Forests, Regression
Tools: R, MS- Excel
Benchmark Bond Trade Prediction
Aim: The bond price prediction can help banks and financial institutions to build their portfolio in diversified manner.
Dataset: 61 attributes, 7.5lakh values
Techniques: Random Forest, Moving Averages, Exponential Moving Averages and ARIMA
Tools: R, Ms-Excel
Prediction Models for Target Marketing
Aim: Use data mining techniques to predict the relevant customers for a retail store. Which product should with its Price have to predict.
Dataset: 25 attribute, 4000 values
Tools Used: R, MS-Excel