Abhishek Vakharia

• Lead and implemented the 20% split and rotation strategy for collections dialer strategy across the loans portfolio increasing the penetration rate by ~9%, the right party contact rate by ~0.35% and the conversion rate by ~2% for the delinquent accounts and reduced the workforce usage time by 20 hours/week • Worked on automating the Pre-Demand Letter Communication strategy for personal loans - increasing the unique open rate by ~1.2% and click rate by ~0.5% • Responsible for strategizing and the implementation of ‘Best time to Call’ strategy for different categories of customers across different times increasing the call pick up rate by ~3% for a single business day • Worked on the Control Reporting for Communication Exceptions in adherence with the different communication policies to assure no breach of process • Designed an automated ETL solution to analyze and track the historical and the current Loan Program Enrollments as well as Payments across the portfolio • Formulated new rules to strengthen and fine-tuned the existing Payment Programs selection criterion for personal loans by analyzing the historical call transcripts using text mining techniques • Maintained and presented key KRIs in relation with the Personal Loans portfolio to the top management using Power Points and Visualizations • Provide impact population and analysis for ad-hoc enterprise problems that affect the customers directly

• Created and implemented the Risk Optimization Placement Model strategy for charged off accounts increasing at risk placement accuracy by ~1% • Designed an automated process to fetch the impact population and calculate the floor and ceiling for student loan settlements resulting in ~2M settlements • Formulated the fundamentals of the Net Present Value Model using feature extraction methodsto understand the dependencies on characteristic parameters for the refined placements of the student loans and personal loans

•Developed rules to identify the first-party fraud applications and accounts using Python, SAS, Snowflake, Teradata SQL •Created a report in Tableau to track the validity of the rules created and interact with the Intelligence teams for verification. Analyzed the error rate and overlap rate for the rules to understand the importance of each rule •Fine-tuned existing rules to improve the accuracy of the rules and created new potential fraud cases •Deployed Google Cloud REST APIs and managed IAM roles to restrict the access to Prod data providing only viewing rights to the users •Developed Google Cloud Functions and Cloud Builds using python scripts to automate the process of rights reduction of a service account •Worked on Migrating data from AWS to GCP and created pipelines for the same

• First hand experience with managing multiple clients •Conducted Landscape Analysis of ARM processing in the enterprise business space based on Apple M1 & M1X chips •Consulted with IT experts to create IT frameworks and translate technical knowledge into business-friendly language to support business apps. •Bootstrapped the partnership deals by identifying the competitive market landscape hence increasing the reach of the startup

• Using Azure VM imported the machine data, cleaned it using python scripts and analyzed it further to calculate the pickup error rate • Assisted client teams by generating reports and daily snapshots of the data available in the Snowflake Tables using SQL queries • The data was further migrated on the remote desktop to create Tableau Dashboard to get better insights about the machine data • Responsible for leading and coordinating amongst various cross functional teams to ensure the integration of the product for 5 clients • Managing the punctual delivery of the product by conducting Bi-weekly sprints and monthly retrospects to better the efficiency of the teams by 10% • Groomed and developed business requirements into user stories via Agile and Scrum methods increasing the use of Business Rules mod by 50%

• Automated an ETL pipeline using AWS Glue, Lambda, Athena and reducing 6 hours per week for team of 5 people • Analyzed the real estate market and focused on the region-wise market analysis using Python and Tableau dashboards • Built data visualizations using Python for incident KPI, enabling stakeholders to make data driven decisions and raising a capital • Researched extensively across the consumer base to understand the company’s target market to develop more effective business strategies

Real estate market demand and price trends were to be reported based on all the given data. Basic idea was to find some pattern in the data and analyse the cause.