svr-regression-prediction

sklearn, tensorflow, random-forest, adaboost, decision-tress, polynomial-regression, g-boost, knn, extratrees, svr, ridge, bayesian-ridge

A python based project to predict the future prices of the top 10 trending cryptocurrencies using ML Algorithms like SVR, Decision Tree and LSTM with an interactive frontend using streamlit. Analysis using PowerBi and has DBMS connectivity.

The dataset used for this project is taken from the official UCI Machine Learning Repository.

Utilized machine learning algorithms to analyze expenses and perform forecasting

The goal of this project is to predict prices using machine learning models, LTSM, and Transformer.

A Machine Learning Model built in scikit-learn using Support Vector Regressors, Ensemble modeling with Gradient Boost Regressor and Grid Search Cross Validation.

Predicting house prices can help determine the selling price of a house in a particular region and can help people find the right time to buy a home.

Regression Machine Learning Project

The Zomato Delivery Time Prediction Application is a machine learning-driven Flask web application designed to predict the estimated delivery time for food orders placed on the Zomato platform.

Stock Price Forecast App is based on Machine Learning. By providing number of days , we can predict trend in Stock Price. The frontend of App is based on Dash-plotly framework. Model is predicting stock price using Support Vector Regression algorithm. App can predict next 5-10 days trend using past 60 days data.

Finding Needles in Emb(a)dding Haystacks: Legal Document Retrieval via Bagging and SVR Ensembles

This repository presents a time series forecasting model for the stock market using SVR and LSTM to build a model that can predict the appropriate time for trading.

Developed a predicting model for automatic bike sharing system using different machine learning and deep learning techniques like XGBoost, SVM, Decision Tree, Random Forest, and CNN and compared the accuracy of different algorithms. And applied grid search and random search to improve the accuracy, score, and reduced the random mean square error.

Development of a predictive model that selects the most cost efficient supplier for a given task

Models for Practice

Physics-informed machine learning and cheminformatics workflow for predicting biochar adsorption capacity of organic water contaminants using RDKit descriptors, molecular fingerprints, ChemBERTa embeddings, and a Streamlit research app.

A Neural Network that predicts the direction of a force experienced by the Syntouch Biotac robotic finger

Machine Learning practice, Linear Regression, Multi-Linear Regression, Polynomial, Support Vector, Decission Tree, Random Forest.

deploy with streamlit community

Recommender System Project This repository contains the implementation of various recommender system algorithms, including KNN, SVM, Decision Tree, and Matrix Factorization. The primary focus is on Matrix Factorization to provide personalized movie recommendations using the MovieLens dataset.