[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.

Comparison of classifier Algorithms on Diabetes Health Indicators Dataset.

Neural Networks ensemble via majority voting in order to classify ships given non-satellite images. All the models have been trained using PyTorch with pretrained weights.

Cognitive Robotics University Exam Project

This project aims to build a regression model that predicts the number of views for TED Talks videos on the TED website.

Regression-PrediksiHargaRumahBoston-kaggle-ensamblemodel-supervisedlearning

Price prediction and appartments recommendation

Various scripts for machine learning

Predicting potential donors using various machine learning models for Charity

This project employs machine learning algorithms to predict customer churn by analyzing historical customer data. It provides actionable insights to enhance customer retention. The models were fine-tuned using hyperparameter optimization and tackled data imbalance with SMOTE, achieving high F1-scores to drive targeted business strategies.

Comparison of classifier Algorithms on bank marketing Dataset

The AdaBoost (Adaptive Boosting) algorithm is a popular ensemble method used in machine learning to improve the performance of weak classifiers. It combines multiple weak classifiers to create a strong classifier, focusing more on the misclassified instances in each subsequent iteration.

Random Forest library university project

Project on Trend Analysis on Pest Occurrence Using Meteorological Data - Information Systems and Business Intelligence (MEng), supervised by Prof. F. Amato, PhD A. Moccardi and PhD M. Fonisto (2024)

A complete pipeline for network intrusion detection comparing label encoding and one‑hot encoding, with SMOTE resampling, feature selection, and ensemble modeling using scikit‑learn and XGBoost, also this was phase one of our University's "CSAI 253- Machine Learning" course.

Ensamble Voting for Financial Time Series

This project builds an interactive Streamlit app for stock price forecasting. It uses an ensemble of Stacked LSTM and Simple RNN models trained on user-uploaded Excel datasets. The app visualizes Bollinger Bands, model performance, and predicts the next day's stock price, offering clear insights with real-time charts and accuracy metrics.

Credit Risk Analysis utilizing imbalanced classification machine learning models

This project is an end-to-end machine learning solution to predict student performance using key features like study time and test scores. It includes exploratory data analysis, model training, and a Flask-based web app for real-time predictions, all built with modular programming for clean and maintainable code.

this repo is about the core machine learning algorithms built in core python and explained trough comments