Aspiring ML Engineer - Python & Data Science Enthusiast

SRIKANTH BYAGARI

Email: *************@*****.*** GitHub: github.com/BYAGARI-SRIKANTH LinkedIn:Linkedin.com/byagarisrikanth Computer Science graduate with strong foundations in Python and Machine Learning. Passionate about building data-driven solutions and eager to contribute as a Trainee Software Engineer in an AI/ML-focused environment. EDUCATION

Vidya Jyothi Institute of Technology, Moinabad Telangana, India Computer Science Engineering: GPA: 6.50/10.0 June 2021 - May2025 Global Junior College,Pargi Telangana, India

Intermediate Course : GPA: 545/1000 August 2019 - May 2021 Zilla Parishad High School,Pargi Telangana, India

Secondary School Certificate : GPA: 7.0/10.0 June 2018 - May2019 SKILLS

● Programming : C, Python

● Libraries : NumPy, Pandas, Matplotlib, Seaborn, Scikit-learn

● Modeling & Optimization : Cross-Validation, Loss Functions, Optimizers, Bias–Variance Tradeoff, Hyperparameter Tuning

● Machine Learning : Supervised Learning (Linear Regression, Logistic Regression, Decision Trees, KNN)

● Data Preprocessing : Handling missing values, Encoding, Scaling, Train-Test Split

● Model Evaluation : Accuracy, Confusion Matrix, Precision, Recall

● Tools : Jupyter Notebook, Google Colab, Git, VS Code

● Database : MySQL (Basic)

PROJECTS

Credit Card Fraud Detection (Classification) LINK April 2025 - April 2025

● Situation : Fraud detection problem with highly imbalanced credit card transaction data.

● Task : EBuild a classification model prioritizing fraud detection over overall accuracy.

● Action : Applied scaling and class imbalance handling, implemented Logistic Regression, and evaluated using Precision, Recall, F1-score, and Confusion Matrix.

● Result: Increased Recall to improve detection of fraudulent transactions while maintaining balanced performance. House Price Prediction using XGBoost (Regression) LINK May 2025 - May 2025

● Situation: Housing prices depend on multiple features with potential missing data affecting model accuracy.

● Task: Build a regression model to accurately predict house prices and improve over basic models.

● Action: Performed feature analysis, handled missing values, implemented XGBoost Regressor, compared with baseline regression models, and analyzed feature importance.

● Result: Achieved improved prediction accuracy over basic models and identified key factors influencing house prices. Medical Insurance Cost Prediction (Regression) LINK Nov 2025 - Nov 2025

● Situation: Insurance charges vary based on demographic and lifestyle factors.

● Task: Develop a regression model to predict medical insurance costs effectively.

● Action: Encoded categorical variables, applied feature scaling and train-test split, and evaluated using R, MAE, and MSE.

● Result: Built a reliable prediction model and identified smoking status as a major cost-driving factor.

Contact this candidate