Skip to content
View abharathkumarr's full-sized avatar

Block or report abharathkumarr

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
abharathkumarr/README.md

Hi there, I'm Bharath Kumar πŸ‘‹

About Me

I am a passionate Software Engineer and AI and DATA Enthusiast, currently pursuing my M.S. in CS at San Jose State University. With a strong foundation in Machine Learning, Deep Learning, and Cloud Technologies, I focus on building intelligent and scalable solutions across various domains, including Natural Language Processing, Computer Vision, and Generative AI.

πŸ”­ I’m currently working on: Developing predictive models and AI-driven applications to solve real-world problems.
🌱 I’m currently learning: Advanced techniques in Large Language Models (LLMs) and cloud-based AI deployments.
πŸ’¬ Ask me about: Machine Learning, AI, Data Engineering, and Cloud Integrations.
πŸ“« How to reach me: LinkedIn or Email
⚑ Fun fact: I love exploring new AI frameworks and contributing to open-source projects.


πŸ›  Technologies I Use

Programming Languages:

  • Python, R, C++, MATLAB

Databases & Data Engineering:

  • MySQL, PostgreSQL, MongoDB, Cassandra, Snowflake, PL/SQL, Hadoop, Spark, Hive, Kafka

Machine Learning & AI:

  • TensorFlow, Keras, PyTorch, Scikit-Learn, OpenCV, Hugging Face, LangChain, LangGraph

Data Visualization:

  • Tableau, Power BI, Matplotlib, Seaborn, Plotly, Google Data Studio

Cloud & Deployment:

  • AWS (EC2, S3, Lambda, SageMaker), Vertex AI, Docker, Kubernetes, FastAPI, Flask, Streamlit, Salesforce

Experimentation & Model Monitoring:

  • MLFlow, DVC, Experiment Tracking, Grafana, Argus, Splunk

Statistical & Analytical Methods:

  • Hypothesis Testing, A/B Testing, PCA, SVD, ANOVA, Bayesian Inference

Core Competencies:

  • Machine Learning, Deep Learning, NLP, Computer Vision, Generative AI, Transformers, Autoencoders, Diffusion Models, Predictive Modeling, Regression, Classification, Clustering, Time Series Forecasting, Data Mining, Data Pipelines

DevOps & CI/CD:

  • Docker, Kubernetes, Terraform, GitHub Actions

Version Control & Collaboration:

  • Git, GitHub, Jupyter Notebook, Visual Studio Code

πŸš€ Key Projects

πŸ”Ή Customer Churn Prediction with ML & Streamlit

πŸ“Œ Technologies: Python, Scikit-Learn, Streamlit, GridSearchCV, Matplotlib, Joblib
πŸ“… Date: Jan 2025

  • Developed a churn prediction model using Logistic Regression, SVM, KNN, Decision Trees, and Random Forest, achieving 94.5% accuracy with GridSearchCV optimization.
  • Built and deployed a Streamlit web app for real-time predictions, integrating data preprocessing, feature engineering, and model training, with Joblib for persistence and Matplotlib for insights.

πŸ”Ή Time Series Forecasting & Visualization

πŸ“Œ Technologies: Python, Pandas, NumPy, Matplotlib, Seaborn, Statsmodels
πŸ“… Date: Oct 2024

  • Conducted exploratory data analysis on time series data, applying resampling, autocorrelation, and stationarity tests to identify trends, seasonality, and anomalies.
  • Developed interactive visualizations using Matplotlib and Seaborn, including line plots, moving averages, and ACF plots, to interpret time-dependent patterns and smooth fluctuations.

πŸ”Ή LLM-Powered Sentiment Analysis

πŸ“Œ Technologies: Python, Scikit-Learn, OpenAI API, Gemini API, Matplotlib, Seaborn
πŸ“… Date: May 2024

  • Implemented sentiment analysis using Large Language Models (LLMs) with OpenAI (ChatGPT) and Google Gemini APIs, leveraging zero-shot and few-shot learning for classification of customer reviews.
  • Performed data preprocessing, including text cleaning, class balancing, and feature engineering. Integrated batch API processing to handle large datasets efficiently, evaluated model performance using confusion matrices and accuracy metrics.

πŸ”Ή Human Activity Recognition with Smartphone Data

πŸ“Œ Technologies: Python, Scikit-Learn, t-SNE, PCA, Matplotlib, Seaborn
πŸ“… Date: Jan 2024

  • Built a predictive model for human activity recognition using smartphone accelerometer and gyroscope data, applying signal processing techniques such as Butterworth filtering and feature extraction in the time and frequency domains.
  • Applied PCA and t-SNE for dimensionality reduction and visualization and optimized classification models (Logistic Regression, SVM, Decision Trees, Random Forest) with hyperparameter tuning and cross-validation for robust activity detection.

πŸŽ“ Certifications

πŸ† Salesforce Certified AI Associate
πŸ† Salesforce Certified Administrator
πŸ† Salesforce Certified Platform Developer I
πŸ† Salesforce Certified Platform Developer II
πŸ† Salesforce Certified Platform App Builder
☁️ AWS Academy Cloud Foundations


πŸ“„ Publications

πŸ“Œ Advanced Hybrid Machine Learning Approaches for Detecting Plant Leaf Diseases
πŸ“– Published in International Journal of All Research Education & Scientific Methods
πŸ”— Read the Paper


πŸ“¬ Contact Me

πŸ“§ Email: pingmebharathkumar@gmail.com
πŸ”— LinkedIn: linkedin.com/in/bharath-kumar-a-6a378b182/
πŸ™ GitHub: github.com/abharathkumarr

Popular repositories Loading

  1. MultiAgent-Industry-Explorer-and-Opportunity-Finder MultiAgent-Industry-Explorer-and-Opportunity-Finder Public

    Python 1

  2. inventorymanagement inventorymanagement Public

    HTML

  3. Customer-Churn-Prediction-with-ML-Streamlit Customer-Churn-Prediction-with-ML-Streamlit Public

    Jupyter Notebook

  4. LLM-Powered-Sentiment-Analysis LLM-Powered-Sentiment-Analysis Public

    Jupyter Notebook

  5. Time-Series-Forecasting-Visualization Time-Series-Forecasting-Visualization Public

    Jupyter Notebook

  6. Human-Activity-Recognition-with-Smartphone-Data Human-Activity-Recognition-with-Smartphone-Data Public

    Jupyter Notebook