Senior Data Scientist
Cambridge Design Partnership
• Currently working on setting up the AI/ML infrastruture at CDP in order to decrease project onboard time and accelerate results
• This cloud-agnostic solution can reduce development costs and development time by ~ 40% and costs by ~ 30% – 40%
• The digital enabler can connect to off the shelf devices for data collection i.e., Apple watch, Oura ring or any custom device. It can preprocess data, analyze the data and eventually generate AI powered insights/services/products based on the application domain
• The healthcare application of this digital enabler can be used in clinical trials to check for drug efficacy, patient monitoring and risk assessment.
• Implemented all areas of AI such as machine learning, deep learning, computer vision and natural language processing in order complete the data science continuum which in turn improved project sales by 31 % in 4 months
• Used the data collected from our digital demonstrator to solve real world healthcare issues such as PCOS (Polycystic ovary syndrome) with patient classification algorithm (user specific logistic regression) with 89% accuracy.
December 2021 - Present
Senior Data Analyst
Finance of America
• Built Portfolio Management Dashboards for enhanced servicing oversight for thousands plus commercial loans and assets adding up to approximately more than a billion dollars
• Automated end of month loan population reporting with dynamic SQL queries using MicroStrategy. This resulted in flexible reporting for any given timeframes
• Created automated cashflow and roll rates for improved validation of end of the month portfolio monitoring. Automation facilitated executive team to scan through portfolios quicker and in a more efficient manner
• Supported the executive team device investment and exit strategies 40% faster with property price forecasting for specific demographics
August 2021 - December 2021
Data Scientist
Cascade Financial Services
• Constructed financial models to calculate Loss curves, Cash flows, Delinquency predictions, Financial durations, and IRR to plan, manage and grow the company's portfolio in the future.
• Created front-end dashboards with Flask and Dash for the executive team to evaluate and modify the mentioned sub-products at will decreasing development time by 40%.
• Performed historical back-testing to validate the models with repect to past data to reduce inaccuracies in future builds.
• Created efficient ETL processes to manage, store and produce economic and psortfolio data. Reduced validation time by 30% using Python, SQL, PGSQL, Jenkins, etc.
• Monitoring system efficiency and reviewing end goal performances to ensure data integrity, quality, and durability.
• Lead 2 company-wide infrastructure migrations. (JAMS to Jenkins, SQL to Postgres SQL)
• Lead system maintenance and performance monitoring tasks.
November 2019 - August 2021
Director of Machine Learning Programs
ODP Solutions (Start-up)
• Built a crypto-centric product, CoinProphet for charting, scanning, sorting, and technical analysis of all the crypto currencies in the world.
• CoinProphet also includes various forecasting algorithms for daily, weekly, monthly forecasts. These are algorithms are back tested to be 85-90% accurate forecasting future prices.
• CoinProphet allows users to do the technical analysis on their favorite crypto currencies and then trade them for profits in the future. Over 14 paper trading accounts CoinProphet was able to generate $96,000 in 4 months.
• Managed a team of 4 data analysts and engineers to create and deploy models for quarterly and long-term revenue outlooks. These models were used to bolster financial projections for investment experts.
• Built predictive model using multivariate regression model using immense financial data. Achieved ~60% better results than experienced wall street analysts.
• Created 3+ machine learning models for risk assessment for stocks and crypto investments to help clients in building their portfolio.
May 2017 - November 2019
Graduate Student Assistant
UNIVERSITY OF CENTRAL FLORIDA
• As Team Leader at Center of Research in Computer Vision team, led an image annotation project, training datasets for raw images to create captcha detection system. Increased image captcha detection accuracy from ~81% to ~92%.
January 2017 - August 2017
DATA ANALYST
CYBERNET.IT
• Created a data scrapping APIs for business intelligence products which paved way for ‘early to market’ plan for those products. Increased profit margins by ~3% per month.
• Proven ability to run SQL queries over multiple databases, created over 1000 queries and stored procedures for Cybernet’s data warehouse reducing the query time by ~50%.
• Created data visualizations using excel, tableau, matplotlib etc. for marketing and business development teams to assess and report meaningful business insights.
• Built HTML dashboards for data insights, data derivations for future references, which yielded ~9% more sales in 11 weeks.
• Created databases through MySQL for software/hardware products and services; making a smooth transition from bulky excel sheets to an organized data warehouse.
May 2013 - May 2016