Principal Data Scientist - Driving Financial Inclusion
Comviva is seeking a mission-driven Principal Data Scientist to join our team focused on driving financial inclusion for the underserved. This role is pivotal in developing, monitoring, and continuously enhancing best-in-class models and algorithms to assess risk, churn, and uptake across the customer lifecycle within the finance industry.
What We Look For:
We are looking for individuals with:
- Expertise in Big Data/ML: Proven ability to build cutting-edge credit, churn, and usage models using advanced algorithms in a Big data/Machine Learning environment. Demonstrated hands-on experience and a track record of delivering projects independently.
- Process Orientation: Capability to build processes that maximize operational efficiency while managing risk across multiple lending cycles. A strong focus on data collection and analysis to drive business iterations and improvements is essential.
- Willingness to Go Above and Beyond: In a dynamic startup environment, responsibilities evolve rapidly. We seek a proactive individual unafraid to take calculated risks and navigate ambiguity.
Job Responsibilities:
- Own the end-to-end delivery of models/algorithms across the customer lifecycle, developing innovative credit risk, churn, and usage models using diverse data sources such as mobile wallet transactions, call data, telecom usage, and customer bureau data.
- Partner with the Data Engineering team to define data pipelines, enhance the feature bank, and build/deploy ML algorithms for both batch and real-time use cases.
- Collaborate with credit policy and portfolio management teams to drive P&L outcomes.
- Build reports for model monitoring and drive continuous enhancements.
Required Qualifications & Skills:
- Bachelor's degree in Engineering from a Tier 1 undergraduate college, with a specialization in computer programming or advanced system analysis (preferred).
- Solid expertise in end-to-end risk model lifecycle management (development, deployment, monitoring).
- Hands-on experience in credit, fraud, and churn model development and deployment.
- Previous experience in PD/EAD/LGD model development/validation.
- Experience in CSI/PSI model monitoring processes.
- Hands-on experience with data extraction using SQL/Pyspark SQL, data cleaning, feature creation, and model building using PySpark/Python on Spark. Experience with large-scale data is a plus.
- Previous exposure to algorithms such as Logistic Regression, Random Forest, XGBOOST, Markov Chain, and PSI/CSI for model monitoring is preferred.
- Experience in strategy performance tracking and swap-in/swap-out analysis.
- Strong entrepreneurial drive.
Good to have:
- Good business understanding of the fintech/consumer finance space.
- Experience working with credit cards or personal lending, particularly in the fintech sector.
- Hands-on experience working with Telecom data.
