Skip to content
View Yashwanth-Kumar-Kotla's full-sized avatar
1 follower · 0 following

Block or report Yashwanth-Kumar-Kotla

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Yashwanth-Kumar-Kotla/README.md

Yashwanth Kumar Kotla

Data Scientist & Machine Learning Engineer

Turning raw data into predictive models and actionable insights

LinkedIn Gmail GitHub Twitter/X

👋 About Me

Master's student in Data Science at Webster University, building end-to-end machine learning pipelines and deploying predictive models as production-ready web applications. My work spans healthcare analytics, regression modelling, classification, and interactive dashboarding with a focus on turning complex data into clear, measurable business value.

Hands-on experience across the full DS lifecycle: from EDA and feature engineering through model training, evaluation, and Streamlit deployment. Comfortable working with Python, SQL, and BI tools in fast-paced, project-driven environments.

🛠️ Skills

Category Technologies
Languages Python · Java · C · SQL
ML / Data Science Scikit-Learn · Pandas · NumPy · Linear Regression · Logistic Regression · SVM · Random Forest · XGBoost · Feature Engineering
Data & EDA Exploratory Data Analysis · Data Cleaning · Correlation Analysis · Seaborn · Matplotlib
Visualisation & BI Tableau · Power BI · Streamlit · HTML5 · CSS3
Deployment & Tools Streamlit · Joblib / Pickle · Docker · Jupyter Notebook · Git · GitHub

Technology Badges

Python Pandas NumPy Scikit-Learn Streamlit MySQL Tableau Java HTML5 CSS3 GitHub

🚀 Featured Projects

1. Medical Insurance Cost Prediction

Regression · Streamlit Deployment · End-to-End ML Pipeline

Item Detail
Problem Predict individual medical insurance charges based on demographic & lifestyle features
Approach Full pipeline — EDA → feature encoding → Linear Regression → evaluation → Streamlit deployment
Key Insight Smoking status is the dominant cost driver (~3–4× charge multiplier); age and BMI are secondary predictors
Metrics R² ≈ 0.77 · MAE ≈ $4,300 · RMSE ≈ $6,200
Stack Python · Pandas · Scikit-Learn · Matplotlib · Seaborn · Streamlit
Live App 🚀 medicalinsurancecostpredict.streamlit.app
Repo Medical-insurance-cost-prediction

2. Diabetes Prediction & Diagnostic Analysis

Classification · Healthcare Analytics · EDA + Tableau Dashboard

Item Detail
Problem Diagnostically predict whether a patient has diabetes using the Pima Indians dataset
Approach Data cleaning → EDA → feature selection → classification model training → Tableau dashboard for stakeholder reporting
Key Insight Glucose level and BMI are the strongest predictive features; class imbalance required careful handling
Stack Python · Scikit-Learn · Pandas · Seaborn · Tableau
Repo (https://github.com/Yashwanth-Kumar-Kotla/Diabetes-Prediction-using-Machine-Learning-with-Python)

3. Sales Data Analysis & Reporting

EDA · Business Intelligence · Automated Reporting

Item Detail
Problem Analyse monthly sales data to surface trends, anomalies, and actionable KPIs for the business team
Approach End-to-end analysis — ingestion → cleaning → aggregation → visualisation → executive-ready report
Key Insight Identified seasonal demand patterns and underperforming product segments; automated ETL reduced reporting overhead
Stack Python · Pandas · Matplotlib · Excel · Power BI
Repo (https://github.com/Yashwanth-Kumar-Kotla/Linear_regression_on_AdvertisingSales_without_sklearn)

📊 ML Pipeline — How I Work

┌──────────────┐    ┌──────────────┐    ┌──────────────────┐
│  Data        │───▶│  EDA &       │───▶│  Feature         │
│  Ingestion   │    │  Visualisation│   │  Engineering     │
└──────────────┘    └──────────────┘    └────────┬─────────┘
                                                 │
                                                 ▼
┌──────────────┐    ┌──────────────┐    ┌──────────────────┐
│  Deployment  │◀───│  Evaluation  │◀───│  Model Training  │
│  (Streamlit) │    │  (R² / MAE)  │    │  (Train/Test)    │
└──────────────┘    └──────────────┘    └──────────────────┘

Every project follows this structured loop — ensuring reproducibility, interpretability, and production readiness.

📈 GitHub Stats

GitHub Stats

Streak

Top Languages

🎯 Currently Learning & Goals

Now Next 6 Months
Deep Learning fundamentals (CNNs, RNNs) Build & deploy a multi-model comparison framework
Advanced feature engineering techniques Explore NLP pipelines (text classification, sentiment)
SQL query optimisation & window functions Pursue AWS or Google Cloud ML certification
SHAP / model explainability methods Contribute to open-source data science tools

Target roles: Data Scientist · ML Engineer · Analytics Engineer

📬 Contact

Channel Link
Email kotla.yashwanthkumar@gmail.com
LinkedIn linkedin.com/in/kotlayashwanthkumar
GitHub github.com/Yashwanth-Kumar-Kotla
Twitter / X x.com/@yashkotla

Open to internships, graduate roles, and project collaborations in Data Science & Machine Learning. Feel free to reach out.

Popular repositories Loading

  1. aura-dual-intelligence aura-dual-intelligence Public

    GPT-4 + Gemini collaboration engine. Dual-intelligence system where two models critique, evaluate, and synthesize answers for higher accuracy and deeper reasoning.

    JavaScript 1

  2. Yashwanth-Kumar-Kotla Yashwanth-Kumar-Kotla Public

  3. Job_data_analysis Job_data_analysis Public

    Jupyter Notebook

  4. Walmart_Exploratory_Data_Analysis Walmart_Exploratory_Data_Analysis Public

    Python

  5. Yashwanth_portfolio Yashwanth_portfolio Public

    TypeScript

  6. Rock-or-Mine-Predictor-using-supervised-ML Rock-or-Mine-Predictor-using-supervised-ML Public

    Jupyter Notebook