Data Science, Data Analysis, Business Analysis, Project Management

MOHIT KUMAR

**************@*******.***

cell-965-***-****

CAREER OBJECTIVE

Data Scientist with 4+ years of experience executing data-driven solutions to increase efficiency, accuracy, and utility of internal data processing. Experienced at creating data regression models, using predictive data modeling, and analyzing data mining algorithms to deliver insights and implement action-oriented solutions to complex business problems.

PROFESSIONAL EXPERIENCE

MetLife GOSC, Noida, India Sep.2014- Till Present

Data Scientist

Python

Machine learning

Data science Data analytics

Reporting and Analytics

Data-Driven Decision making

Data analysis and data visualization

Data quality

SQL (SSMS)

NLP

OpenCV Face and Image recognition

Speech Recognition Python

Audio data processing

Speech to text programming on Python

5 years of data analytics, data management experience in data-driven decision-making, driving various data quality projects through a unified and governed data management processes.

Working knowledge of Python & SQL for data mining, manipulation, and analysis.

Acquiring data from primary or secondary data sources and analyzing data by using statistical techniques and providing ongoing reports Exposure in various Multivariate

Analysis Techniques which includes Cluster Analysis, Regression techniques, and Machine learning concepts

Interpreting data, analyzing results using statistical techniques and providing ongoing reports

Present detailed reports about the meaning of gathered data to members of management and help them identify scenarios utilizing modifications in the data.

Forecasting next year’s renewal cost/rates through the Machine Learning tool (Predictive Model) using historical experience to evaluate the appropriateness of an insurer’s fully insured renewal calculation.

Data extraction, manipulation using Python/Machine Learning

1.Risk Detector for Insurance Fraud

Insurance frauds cover the range of improper activities which an individual may commit in order to achieve a favorable outcome from the insurance company. This could range from staging the incident, misrepresenting the situation including the relevant actors and the cause of the incident and finally the extent of damage caused.

Covering-up for a situation that wasn’t covered under insurance (e.g. drunk driving, performing risky acts, illegal activities, etc.)

Misrepresenting the context of the incident: This could include transferring the blame to incidents where the insured party is to blame, failure to take agreed-upon safety measures

Inflating the impact of the incident: Increasing the estimate of the loss incurred either through the addition of unrelated losses (faking losses) or attributing increased cost to the losses

2. Predicting premium default and loos for upcoming years

This project covers the due payments based on debt history and income. By using machine learning predictions, we were able to able to predict the value of the customer. This machine learning model helped the company to retain the customer and maintain the financials.

3.Real-time face recognition software

A real-time face recognition system is capable of identifying or verifying a person from a video frame. This model was designed for some specific customers in order to log in online and update the record. The model helped customers in terms of cybersecurity.

4. Recognition of Handwritten ZIP Codes

In this Project, we describe the OCR and image processing algorithms used to read destination addresses from non-standard letters (flats). We first describe the sequence of image processing and pattern recognition algorithms needed to solve the difficult task of reading mail addresses, especially handwritten ones. The project concentrates mainly on the two classifiers used to recognize handprinted digits used to classify scaled digit-features. The other classifier extracts the structure of each digit and matches it to several prototypes. Different digits represented by the same graph are then discriminated by classifying some of the features of the digit-graph with small neural networks. We also describe some approaches for the segmentation of the digits in the ZIP code, so that the resulting parts can be processed and evaluated by the classifiers

IBM INDIA, Noida, India Jan.2012-Sep.2014

Senior Technical Support Officer

Joined IBM as an IT Analyst

Been a part of the IT team which acts as the bridge between the Client and End-user.

Preparing the log of Calls and Emails in various repositories and assisting users with their various issues over the phone and through emails.

Proficient with the Windows platform.

Assisting Business users by way of scheduling calls and conferencing with them to understand the nature of the problem and coming up with the best possible solution.

Supervising the new hires and providing the coaching to them and briefing the team with the latest changes and updates.

EDUCATION

Bachelor of Commerce, 2011

Safe Agile certified

Prince 2 Trained

ITIL Trained

Certified in Data Science, Machine Learning, Python

Trained in Lean Six Sigma

Diploma in computer application

PERSONAL DETAILS

Date of Birth 26th of January 1990

Gender Male

Language (Fluent) Hindi and English

Language (Learner) Japanese

Contact this candidate