Skip to content
View suzaladhikari's full-sized avatar
4 followers · 5 following

Block or report suzaladhikari

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
suzaladhikari/README.md

Undergraduate researcher in CS & Mathematics at Caldwell University Investigating federated learning for privacy-preserving network intrusion detection — specifically how aggregation algorithms like FedNova address minority silo failure under non-IID data distributions.

Currently building: Clarity, a volatility forecasting pipeline (GARCH vs. LSTM) Open to: Fall 2026 ML/AI internships and research collaborations

LINKEDIN ORCID

Pinned Loading

  1. clarity clarity Public

    Volatility forecasting system comparing LSTM against GARCH(1,1) baseline across 20 stocks — end-to-end MLOps pipeline with FastAPI, Docker, and Streamlit.

    Python

  2. federated_learningIDS federated_learningIDS Public

    Empirical comparison of FedAvg, FedProx, and FedNova for network intrusion detection under pathological non-IID partitioning on CIC-IDS-2017.

    Jupyter Notebook 2

  3. Network_Intrusion_Detector Network_Intrusion_Detector Public

    Two-stage XGBoost-based hierarchical intrusion detection system for attack detection and severity classification using KDD Cup 99 dataset.

    Jupyter Notebook

  4. customer_churn- customer_churn- Public

    End-to-end MLOps customer churn prediction system using Random Forest, FastAPI, Streamlit, and Docker with real-time inference and cloud deployment.

    Jupyter Notebook

  5. CardioRiskPredictor CardioRiskPredictor Public

    End-to-end ML system for cardiovascular disease risk prediction with interactive Streamlit UI and multi-model evaluation pipeline.

    Jupyter Notebook

  6. la-weather-statistical-analysis la-weather-statistical-analysis Public

    Exploratory data analysis and hypothesis testing of weather patterns in Los Angeles using non-parametric statistical methods.

    Jupyter Notebook