Situation: Our bank needed to automate and optimize business reporting for daily excess and past-due reports, specifically for our business and credit risk teams. The goal was to reduce daily turnaround time (TAT) and enhance revenue collection across 14 markets in Africa & the Middle East.

·         Task: I was appointed to lead a team of three, including two data analysts and one data scientist, to develop a 2-phase initiative for automating credit reporting and integrating machine learning algorithms to improve credit risk management.

·         Action:

1.     In Phase 1, we created data tables, modified data pipelines, cleansed the data, and built connections to Tableau for visualization.

2.     Our team automated workflows to download, segregate, and tabulate data into live dashboards, eliminating manual activities and reducing time spent by 75%.

3.     We reduced touchpoints from 3 to 1, centralizing activities in the country by business users.

4.     In Phase 2, we integrated supervised machine learning algorithms (decision trees and random forests) to credit score accounts and better inform credit risk managers' decisions.

·         Result: The successful implementation of this initiative led to significant improvements:

1.     Reduced daily TAT by more than 75% (from 2 man hours to less than 30 minutes).

2.     Reduced touchpoints by 33%.

3.     Saved approximately $25K per annum across the business teams.

4.     Enabled faster resolution of excess or past-due accounts, safeguarding the bank from credit exposures.

5.     Optimized revenue collection in excess of USD 500K as at Q4 2022 through the use of machine learning algorithms.

This project not only demonstrated my team's agility and innovation, but it also earned recognition from Senior Management. I received the CEO Award in December 2022, under the Agility Category, for my commitment to solving business challenges through collaboration and cross-functionality