This role is for one of Weekday’s clients

Min Experience: 6+ years
Location: Bengaluru
JobType: full-time

We are looking for an experienced Lead Data Scientist with strong expertise in data science, machine learning, and credit risk modelling. The ideal candidate will lead the development and deployment of advanced analytical models that support credit decision-making, risk assessment, collections management, and business growth.

In this role, you will work closely with business stakeholders, product teams, and engineering teams to identify data-driven opportunities, develop scalable machine learning solutions, and translate complex analytical insights into measurable business outcomes. You will own the end-to-end model lifecycle, from data exploration and feature engineering to model development, deployment, monitoring, and continuous improvement.

Requirements

Key Responsibilities

1. Credit Risk Modelling and Analytics

• Design, develop, and deploy end-to-end credit risk scorecards and predictive models across the customer lifecycle, including application scoring, behavioural scoring, collections scoring, loan pricing, loss forecasting, and cross-selling.
• Apply statistical and machine learning techniques, including linear and logistic regression, random forests, boosting and bagging algorithms, and dimensionality reduction.
• Evaluate model performance, stability, predictive accuracy, and business impact to improve credit decisions and risk management outcomes.
• Develop data-driven strategies to enhance underwriting, portfolio monitoring, collections effectiveness, and customer segmentation.

2. Data Science Strategy and Business Partnership

• Collaborate with stakeholders across business, product, risk, and engineering teams to identify opportunities for leveraging internal and external data.
• Develop and maintain a data science use-case roadmap aligned with business priorities and product objectives.
• Act as a data strategist by identifying new datasets and analytical capabilities that can enhance existing products and enable new data-driven solutions.
• Translate business requirements into analytical problems, modelling approaches, and actionable recommendations.

3. Data Preparation and Exploratory Analysis

• Extract, process, clean, and validate large datasets to ensure data quality, consistency, and reliability.
• Enhance data collection processes and establish robust data preparation and validation practices.
• Conduct exploratory data analysis to identify trends, relationships, patterns, and potential predictive signals.
• Perform feature selection, feature engineering, and data mining using appropriate statistical and machine learning methods.
• Develop data visualisations and dashboards to communicate findings and track model performance and business impact.

4. Machine Learning and Model Development

• Build, train, validate, and optimise machine learning models using appropriate statistical and computational techniques.
• Apply algorithms such as k-nearest neighbours, Naive Bayes, support vector machines, decision trees, ensemble methods, and artificial neural networks.
• Evaluate emerging algorithms and research developments to identify opportunities to improve model performance and analytical capabilities.
• Establish robust model validation practices, assess algorithmic limitations, and ensure models are appropriate for their intended business applications.
• Explore deep learning techniques where they offer meaningful advantages for predictive modelling.

5. Productionisation and Model Monitoring

• Build and maintain automated training pipelines to support reliable model development and deployment.
• Collaborate with engineering teams to integrate models into production systems and data products.
• Define model quality standards, validation parameters, infrastructure requirements, and deployment processes.
• Monitor production models and data pipelines, troubleshoot performance issues, and lead debugging efforts.
• Establish continuous model refinement and monitoring processes to maintain model accuracy, stability, and business relevance.
• Develop dashboards and reporting mechanisms to track model outcomes, operational performance, and business impact.

Must-Have Skills

• Strong expertise in Credit Risk Modelling, Machine Learning, and Data Science.
• Hands-on experience developing credit risk scorecards, including application, behavioural, and collections scorecards.
• Proficiency in Python and SQL for data manipulation, statistical analysis, and model development.
• Strong foundation in applied statistics, including probability distributions, hypothesis testing, regression, and statistical inference.
• Excellent understanding of machine learning algorithms, their applications, and their advantages and limitations.
• Experience with feature engineering, model validation, predictive analytics, and production model deployment.
• Strong problem-solving skills with an emphasis on practical product development and business impact.
• Excellent written and verbal communication skills, with the ability to collaborate effectively across technical and business teams.

Good-to-Have Skills

• Experience with XGBoost and other gradient-boosting frameworks for predictive modelling.
• Proficiency in data science libraries and frameworks such as NumPy, Pandas, SciPy, Scikit-learn, TensorFlow, Keras, R, or MATLAB.
• Experience with data visualisation tools and libraries such as D3.js, ggplot2, or equivalent platforms.
• Familiarity with NoSQL databases such as MongoDB, Cassandra, or HBase.
• Experience with distributed computing and big data technologies such as Hadoop, MapReduce, Hive, and Apache Spark.
• Knowledge of deep learning methods and their practical applications in risk analytics.
• Experience with model deployment, production monitoring, and scalable machine learning pipelines.

Experience and Qualifications

• Experience: 5–10 years in data science, statistical modelling, machine learning, or related analytical roles.
• At least 1 year of relevant experience in credit risk, lending, financial services, or collections management.
• Bachelor's, Master's, or Ph.D. degree in Statistics, Mathematics, Computer Science, or another quantitative discipline, preferably from a top-tier institution.
• Demonstrated experience building and deploying analytical models that solve real-world business problems.