Portfolio - Karthik Mohan

Karthik Mohan

Data Scientist

Resume

1

Python Project

About Me

🔹 Applied Data Scientist and AI Engineer with hands-on experience building, validating, and deploying machine learning and time-series analytics in automotive R&D environments.

🔹 Specialized in translating complex vehicle telemetry and fatigue theory into production-ready models and tools that improve reliability, reduce validation effort, and enable data-driven engineering decisions.

🔹 Led end-to-end analytics initiatives, covering feature engineering, predictive modeling, physics-informed methods, and algorithm productization with real-world vehicle validation.

🔹 Delivered scalable, high-impact solutions adopted across multiple teams, directly influencing product quality, system performance, and engineering efficiency.

Key Skills

Machine Learning

Time-Series Analytics

Feature Engineering

Predictive Modeling

Big Data & Spark

Algorithm Deployment

My Projects

Healthcare Insurance Premium Prediction Using Machine Learning

Domain/Function: Healthcare Analytics | Predictive Modeling | Insurance Risk Analysis

My Experience

Data Scientist @ Mercedes Benz Research and Development India - aug 2023 to Present

Engineered an ML-based brake pad wear prediction model using telemetry and test-bench data, applying feature engineering and real-vehicle validation to achieve ~90% accuracy and reduce maintenance downtime by 25%.
Designed a temperature-weighted damage KPI reliability model by evaluating fatigue and mathematical techniques, improving axle joint assessment accuracy and cutting low-temperature validation testing by 33%.
Productized a time-series virtual sensor for maneuver detection by developing iterative detection logic and deploying a standalone EXE across departments, achieving >95% accuracy and significantly reducing manual validation effort.
Implemented a four-point Rainflow fatigue analytics pipeline to translate real-world vehicle load data into deployable damage metrics, enabling supplier-ready ECU feasibility for large-scale customer vehicle durability monitoring.

Awards & Certificate

Master Machine Learning for Data Science & AI: Beginner to Advanced

Python: Beginner to Advanced For Data Professionals

SQL for Data Science

Math and Statistics For AI, Data Science

Let's Connect

Feel free to get in touch with me. I am always open to discussing new projects, creative ideas or opportunities to be part of your visions.

Download Resume

Resume

Mail Me

[email protected]

https://www.linkedin.com/in/-karthikmohan

Call Me

+91 8892786544

GitHub

https://github.com/1karthikmohan

Python Project

Healthcare Insurance Premium Prediction Using Machine Learning

Domain/Function: Healthcare Analytics | Predictive Modeling | Insurance Risk Analysis

Built a machine learning model to predict healthcare insurance premiums based on customer demographics and health factors. Applied data preprocessing, feature engineering, and regression techniques to estimate premiums accurately and support risk-based pricing decisions.

Other Tools

Pandas

Numpy

scikit-learn

Matplotlib

jupyter

seaborn

Exploratory data analysis showing the relationship between customer health attributes and insurance premium distribution.

Model performance comparison and feature importance analysis highlighting key factors influencing insurance premium prediction.

Project Details

This project focuses on predicting healthcare insurance premiums using machine learning techniques. The dataset includes demographic and health-related attributes such as age, BMI, smoking status, number of dependents, and region. Data preprocessing involved handling categorical variables, scaling numerical features, and exploratory data analysis to identify key premium drivers. Multiple regression models were evaluated, including Linear Regression and tree-based approaches, to compare performance and interpretability. The final model achieved strong predictive accuracy and highlighted smoking status, age, and BMI as the most influential factors affecting insurance costs. This project demonstrates the practical application of data science in healthcare insurance pricing, risk assessment, and cost optimization.