Available for Sports Analytics Roles

Soumya
Karmakar.

I am a

Passionate about Data Science, Machine Learning, Statistical Modeling and Sports Analytics. Combining analytical thinking with competitive sports experience to solve real-world problems through data-driven solutions.

Download Resume Explore Projects Sports Portfolio Contact Me
Soumya Karmakar
Statistics Experience
5+ Years
01 / About

Where Statistics Meets the Court

Soumya Karmakar is an M.Sc. Statistics and Computing student at Banaras Hindu University and a National-Level Basketball Player. His interests lie at the intersection of Statistics, Data Science, Machine Learning, Deep Learning, and Sports Analytics.

Through academic training and competitive sports experience, he has developed strong analytical, problem-solving, teamwork, and leadership skills. He is passionate about leveraging data-driven approaches to solve real-world problems and create meaningful insights from complex datasets.

National-Level Athlete
Represented West Bengal
M.Sc. Student
Banaras Hindu University (2025-2027)
Statistics Graduate
St. Xavier's College, Kolkata (2022-2025)
Sports Analytics
Enthusiast
02 / Education

Academic Journey

From West Bengal classrooms to the halls of Banaras Hindu University.

AUG 2025 – PRESENT

Banaras Hindu University

M.Sc. Statistics and Computing

SGPA: 7.0/10
Sep 2022 – Jul 2025

St. Xavier's College (Autonomous), Kolkata

B.Sc. Statistics (Honours)

CGPA: Class se zyada court pe tha 😔🏀/ 10
2022

Belkulai CKAC Vidyapith

Higher Secondary Examination

87.2%
2020

Joynagar Pallisree Vidyaniketan

Secondary Examination

83.7%
03 / Skills

Tools of the Trade

A blend of statistical rigor, programming fluency, and modern data tooling.

Statistics

  • Statistical Inference90%
  • Probability Theory88%
  • Regression Analysis92%
  • Design of Experiments80%
  • Time Series Analysis78%

Machine Learning

  • Regression90%
  • Classification88%
  • Neural Networks75%
  • Clustering82%
  • Predictive Analytics85%

Programming

  • Python92%
  • R88%
  • SQL85%
  • C70%

Tools & Visualization

  • Power BI85%
  • Excel90%
  • Minitab80%
  • MySQL82%
  • Git78%
  • Jupyter / Colab92%
04 / Services

What I Can Build For You

From clean exploratory analysis to production-ready ML pipelines.

Data Analysis

Turning raw data into clear, actionable insight.

Statistical Consulting

Experimental design, inference & methodology guidance.

Machine Learning Solutions

Custom ML pipelines for prediction and classification.

Predictive Modeling

Forecasting outcomes from historical & live data.

Sports Analytics

Player, team, and game-level performance models.

Dashboard Development

Power BI dashboards that tell the story.

Research Data Analysis

Academic-grade rigor for theses and papers.

SQL Database Analysis

Query, model and explore relational data.

Academic Analytics Projects

Mentoring & collaborating on student projects.

05 / Projects

Selected Work

Building, breaking, and rebuilding models — one project at a time.

Featured Project

Predicting NBA All-Starswith PCA & Logistic Regression

A data-driven approach that fuses dimensionality reduction with classical statistical modeling to predict which NBA players will make the All-Star roster based on per-game and advanced stats.

  • PCA Implementation
  • Logistic Regression Modeling
  • NBA Player Analytics
  • Sports Data Visualization
  • Prediction Dashboard
View Project GitHub Repository
Language
R
Techniques
Principal Component Analysis (PCA)
Logistic Regression
Domain
Sports Analytics
Dataset
NBA Regular Season Player Statistics
Objective
Predict NBA All-Star selections using statistical performance indicators.
Featured Project

AI-Powered Precision OncologyCancer Drug Response Prediction

An AI-driven precision oncology system that predicts cancer drug sensitivity using pharmacogenomic data and recommends promising therapeutic options. The project combines machine learning, deep learning, explainable AI, and a drug recommendation engine to support cancer treatment research.

  • CatBoost
  • Neural Networks
  • SHAP Explainability
  • Drug Recommendation System
  • Precision Oncology
  • Healthcare Analytics
GitHub Repository
Language
Python
Techniques
CatBoost Neural Networks SHAP Machine Learning
Domain
Healthcare Analytics Precision Oncology
Dataset
Genomics of Drug Sensitivity in Cancer (GDSC)
Objective
Predict cancer drug response and recommend effective therapeutic options using pharmacogenomic data.
Model Performance
Best Model: CatBoost Accuracy: 83.45% ROC-AUC: 0.9216

In the Pipeline

Healthcare Analytics
Deep Learning
Computer Vision
Sports Analytics
Statistical Modeling
AI Applications
06 / Certifications

Continuous Learning

Investing in knowledge from world-class institutions.

Specialization

Machine Learning Specialization

Stanford University & DeepLearning.AI

Instructor: Andrew Ng

View PDF
Elite

Data Analytics with Python

NPTEL · IIT Roorkee

Elite Certification

View PDF
IBM
Professional Certificate

Introduction to Deep Learning & Neural Networks with Keras

IBM

Coursera · Completed June 2026

Completed foundational training in Deep Learning and Neural Networks using Keras, covering neural network architectures, forward and backpropagation, activation functions, model training, and practical deep learning workflows.

07 / Leadership & Responsibilities

Leadership & Responsibilities

Leadership experiences that strengthened my teamwork, communication, organization, mentoring, and decision-making abilities both on and off the basketball court.

4+
Leadership Roles
20+
Events Organized
2 Years
Team Selector
2 Teams
Coached
2026

Basketball Coach – Inter College Tournament

Institute of Science, BHU & Faculty of Law, BHU

Served as the coach of the women's basketball teams of the Institute of Science, BHU and Faculty of Law, BHU during the Inter College Basketball Tournament held at Vasanta College for Women, Varanasi. Provided tactical guidance, game planning, player development, and team coordination throughout the tournament.

2025

Organizing Committee Member – Epsilon Delta 2025

Department of Statistics, St. Xavier's College, Kolkata

Contributed to planning, coordinating, and organizing the annual departmental fest.

2025

Sports Committee Member – Cofradia 2025

St. Xavier's College Hostel

Collaborated with a team to organize 20+ sports and gaming events, ensuring smooth execution and participation.

2022 – 2023

Selector – CISCE Nationals

CISCE West Bengal Basketball Teams

2022: U14, U17 & U19 Boys 2023: U14, U17 & U19 Boys U14, U17 & U19 Girls Served as a selector for the CISCE West Bengal Basketball teams across multiple age categories for two consecutive years.

08 / Sports

National-Level Basketball

Nine years on the hardwood — from West Bengal courts to All India Inter University.

Soumya Karmakar — National-Level Basketball Player
Position
SG
Height
6'1"
State
WB
2019

Youth National Championship

Represented West Bengal.

2024

Division 1 League Champion

Won the West Bengal Division 1 Basketball League with Xaverians' Club.

2026

All India Inter University 3x3 Basketball Championship

Represented Banaras Hindu University.

View Full Sports Portfolio
07 / Contact

Let's Build Something

Open to research collaborations, sports analytics roles, and data science opportunities.

Location
Kolkata, West Bengal, India
Social
Status
Available for new projects & roles