Role: Data Modeler

Position Type: Full-Time Contract (40hrs/week)

Contract Duration: Long term

Work Schedule: 8 hours/day (Mon-Fri)

Location: Hybrid - Onsite 2 days a week in Hyderabad

This individual will be responsible for the following:

· Independently execute analytical projects focused on retail credit risk modeling, model validation, business intelligence, development of underwriting strategies, limit assignment strategies and other engagements around customer credit lifecycle from data integrity evaluation through solution documentation and implementation.

· Develop and lead statistical and machine learning efforts in relation to assigned projects. The projects will leverage initial data preparation steps, Exploratory Data Analysis, attributes derivation, Bureau inference and reject inference, model training and validations, model documentation and model deployment via containerization.

· Execute multiple complex client projects with minimal guidance and troubleshoot technical issues.

· Collaborate with internal and external stakeholders to determine the appropriate project parameters and performance measures to be applied, as well as requirements for decision tool and strategy implementation and monitoring.

· Interpret analytical project results, identify trends and issues, and recommend alternatives to support business objectives.

· Leverage a broad stack of technologies: SQL, PySpark, Python, AWS and more to obtain insights from large volumes of data.

· Develop and QA statistical models, building using Machine Learning techniques (Logistic Regression, Random Forest, XGBOOST).

· Develop and QA business intelligence reports from data and provide recommendations to internal stakeholders.

· Run validation of different models and prepare performance charts with key model performance characteristics.





· Participate in the QA of variables and models for logic and specification accuracy and in support of implementation of statistical models and other decision tools.

· Explore and research opportunities to improve and expand upon current processes via automation or creating best practices.

· Support the sales, development, enhancement, or maintenance of analytical products or processes. UAT of new product/platform enhancements.

· Perform R&D; in statistical analysis to help with improvement of existing statistical products.

· Write programs in Python/PySpark to automate and streamline existing repetitive processes.

· Maintain and develop Tableau dashboards.

What the successful candidate brings:

· Bachelor's degree in mathematics, Computer Science, Statistics or a related field.

· 5+ years of experience with statistical and quantitative analysis, Machine Learning, Statistical Modeling, including large scale data manipulation.

· Knowledge of statistical models & practical experience in predictive model development in Consumer Credit Lifecycle, predominantly consumer underwriting (using Python, PySpark, R, SAS).

· Capable of accurately joining large data sets from multiple data sources, created complex logic for data cleaning & outlier detecting, and build & refine business rules to validate and monitor the model forecast.

· Expert experience with data querying languages (e.g. SQL) & scripting languages (e.g. Python).

· Proven ability to think creatively, solve problems, learn quickly, work independently, handle ambiguity, and adapt to change in a fast-paced setting.

· Excellent written, verbal, and interpersonal communication and presentation skills in English.

· Experience in programming in parallel and distributed computing for Big Data such as MapReduce, Spark, Hadoop, Yarn.

· Financial services industry experience preferred.

· Experience with visualization tools like Tableau/PowerBI.

📌 Data Modeler (Hyderabad)
🏢 SkySys
📍 Hyderabad