Background

Pezesha, has created a holistic financial marketplace for MSMEs. By offering lending, financial education, and debt counselling to borrowers, plus a proprietary credit scoring system to vet MSMEs without a credit history, derisking lending to SMEs. Lower Risks bring commercial banks and capital providers onto Pezesha platform. As a collaborative structure, Pezesha is helping to tackle the $19 Billion financing gap for SMEs. Pezesha is led by a highly experienced and passionate local team with more than 10 years local and international experience in fin-tech, management of growth and technology companies, and unparalleled local market knowledge and reach.

Role Overview

As a Junior Data Scientist, you will support the Data Team in turning raw data into actionable insights that inform credit, product, operations, and business decisions. You will work on real business problems involving customer behavior, lending performance, transaction data, credit risk, and operational analytics. You will also have opportunities to contribute to machine learning and credit-scoring projects under the guidance of senior members of the team. The ideal candidate is curious, analytical, comfortable working with data, and eager to learn.

Core Responsibilities

Data Analysis & Reporting

• Write SQL queries to extract, clean, transform and analyze data.
• Support the preparation of recurring business and portfolio reports.
• Conduct exploratory data analysis to identify trends, patterns, and anomalies.
• Support data requests from Credit, Product, Operations, Finance, and other teams.
• Help validate reported metrics and investigate discrepancies in data.

Credit & Portfolio Analytics

• Conduct analysis of loan repayment and customer behavior.
• Analyze lending metrics such as repayment rates, PAR, DPD, disbursements, collections, and portfolio performance.
• Perform customer segmentation analysis.
• Support monitoring of credit risk indicators and model performance.
• Contribute to credit scoring improvement ideas.

Insights & Reporting

• Respond to data and analysis requests from cross-functional teams (Operations, Product, Finance, Credit).
• Prepare weekly and monthly reports for internal stakeholders and external lenders, covering portfolio performance and borrower analytics.
• Support ad-hoc data deep dives to identify performance trends, risks, or operational issues.

Model Experimentation Support

• Work closely with senior data scientists to prepare datasets and conduct performance evaluations for machine learning and scorecard prototypes.
• Participate in feature engineering, validation testing, and performance tracking of classification and credit scoring models.

Documentation & Best Practices

• Maintain clear, up-to-date documentation for datasets, metrics definitions, SQL queries, ETL workflows, and dashboards.
• Contribute to a shared knowledge base including SQL snippets, data dictionaries, and ETL logic to support collaboration and onboarding.
• Follow and promote data quality, QA, and reproducibility best practices.

• Write SQL queries to extract, clean, transform and analyze data.
• Support the preparation of recurring business and portfolio reports.
• Conduct exploratory data analysis to identify trends, patterns, and anomalies.
• Support data requests from Credit, Product, Operations, Finance, and other teams.
• Help validate reported metrics and investigate discrepancies in data.
• Conduct analysis of loan repayment and customer behavior.
• Analyze lending metrics such as repayment rates, PAR, DPD, disbursements, collections, and portfolio performance.
• Perform customer segmentation analysis.
• Support monitoring of credit risk indicators and model performance.
• Contribute to credit scoring improvement ideas.
• Respond to data and analysis requests from cross-functional teams (Operations, Product, Finance, Credit).
• Prepare weekly and monthly reports for internal stakeholders and external lenders, covering portfolio performance and borrower analytics.
• Support ad-hoc data deep dives to identify performance trends, risks, or operational issues.
• Work closely with senior data scientists to prepare datasets and conduct performance evaluations for machine learning and scorecard prototypes.
• Participate in feature engineering, validation testing, and performance tracking of classification and credit scoring models.
• Maintain clear, up-to-date documentation for datasets, metrics definitions, SQL queries, ETL workflows, and dashboards.
• Contribute to a shared knowledge base including SQL snippets, data dictionaries, and ETL logic to support collaboration and onboarding.
• Follow and promote data quality, QA, and reproducibility best practices.

• SQL
• Data Analysis
• Data Cleaning
• Data Transformation
• Exploratory Data Analysis
• Reporting
• Machine Learning (basic understanding)
• Credit Scoring (basic understanding)
• Feature Engineering
• Documentation
• Data Quality Assurance
• Reproducibility

• BA/BSc/HND
• Curiosity
• Analytical skills
• Comfort working with data
• Eagerness to learn