Data Scientist Machine Learning

SHASHWAT DUBEY

+1-925-***-**** *****************@*****.*** Linkedin Pleasanton,CA

Summary

Data Scientist with over 2 years of experience applying advanced statistical methods and machine learning algorithms in the finance industry. Hold a dual degree: MBA from NMIMS, India, and a Master's in Business Analytics from Purdue University, USA.Proven expertise in developing predictive models, such as investor profiling and revenue forecasting, to drive targeted marketing strategies and improve business decision-making. Proficient in leveraging tools like SQL, Python, AWS, and Snowflake to build efficient data pipelines and create interactive dashboards. Skills

Programming Languages:SQL, Python, R, Spark

Design and Visualization Tools:Quicksight, Tableau,Power BI, SAS Visual Analytics, Excel Production:AWS EC2, Batch, Glue Studio, GIT, Docker,Kubernetes, Cloud Computing, API AI/ML:Statistics, Experimental Designing, PredictiveModelling, Clustering, Hypothesis Testing, NLP, Deep Learning Databases:Amazon RDS, Snowflake, Athena, Dbeaver,Amazon Redshift, DynamoDB, SQL Server, Big Data Work Experience

DSP Asset Managers Mumbai, India

Data Scientist Jan 2022 - Dec 2023

• Developed and implemented a monthly scorecard-based ranking system accessible via API, prompting stakeholders to view their current rankings and key metrics upon login.

• Designed and implemented models for investor profiling with 90% accuracy, enhancing targeted marketing efforts.

• Predicted investor actions through SIP (Systematic Investment Plan) Cancellation and Redemption prediction models, improving proactive engagement strategies.

• Identified strong patterns in fund purchasing behavior through the Market Basket Analysis model for cross-selling funds, improving the average fund holding per investor by 30%

• Performed A/B testing to assess the impact of message frequency and cross-selling strategies on conversion rates and investor retention, leading to a 15% increase in new investor sign-ups and a 10% reduction in churn

• Utilized Google Analytics to track and analyze user behavior on DSP's website and app, identifying key traffic patterns and user engagement metrics, resulting in a 12% increase in lead conversions and a 10% improvement in user retention

• Designed and implemented an intermediate data layer in Snowflake to streamline data processing for dashboards and analytical use, improving data accessibility and query performance for reporting and decision-making Bonutti Technologies Purdue, USA

Analytics Consultant Jan 2021 - Mar 2021

• Built an application on Python that predicts the probability of relapse post-corrective knee surgery with 90% accuracy

• Performed extensive data cleaning and exploratory data analysis to identify key areas associated with knee problems

• Used survival curves to demonstrate the impact of different parameters on knee recovery over time post-surgery Growthsource Mumbai, India

People Analyst Intern Oct 2020 - Dec 2020

• Created interactive dashboards using Power BI based on parameters relating to and covering the employee workforce

• Streamlined the data collection process for the company to make more informed decisions HUDL Mumbai, India

Sports Analyst Aug 2017 - Mar 2018

• Analyzed performance data from NBA and NFL games, delivering key insights to optimize strategies for coaching staff

• Validated and reviewed game footage, ensuring accurate tagging of player actions for reliable performance analysis

• Improved data collection and reporting workflows, speeding up insights delivery efficiency by 20% Education

Purdue University, Krannert School of Management, Indiana, USA Master of Science, Business Analytics and Information Management Jan 2021 - Aug 2021 NMIMS, School of Business Management, Mumbai India Master of Business Administration, Decision Science and Analytics Jun 2019 - Aug 2021 Certifications and Achievements

Completed the AI/ML for geodata course conducted by the Indian Space Research Organization 2024 Completed the Associated Data Engineering course, Datacamp 2024

Contact this candidate