I developed a sophisticated ML model using LLMs to predict user preferences in chatbot interactions.implemented a comprehensive data preprocessing pipeline,including feature extraction and encoding,to optimize performance. conducted extensive hyperparameter tuning and evaluation, enhancing accuracy and in AI-driven conversational systems.

Using various supervised learning estimators in Sci-Kit Learn to get the best prediction accuracy if possible for the pima indians dataset.

Predicts early diabetes risk using SMOTE for balancing and KNN for classification.

Using scikit-learn RandomizedSearchCV and cross_val_score for ML Nested Cross Validation

A Linear Regression project to analyze and predict sales based on TV, Radio, and Newspaper advertisement budgets.

Classifies e-commerce user intent to purchase using ML models on session data.

In this project, I have developed a Machine Learning model to predict whether users will click on ads. By analyzing various characteristics of users who click on ads, we can gain valuable insights and optimize ad campaigns for better engagement.

Model-Validation-Methods

Built Random Forest classifier from scratch on top of Scikit Learn decision trees. Using Scikit Learn to create data cleaning pipelines, perform grid searches for hyper parameter tuning, and decision tree modeling

This is a Kaggle Dataset where we classify the cars using their various features. Here I used plotly to visualize the Accuracy Scores. Also I used CrossValScore to get More accurate Accuracy Score.

Iris dataset

End-to-end ML pipeline for Titanic survival prediction — data preprocessing, Random Forest classifier, and a FastAPI web app with prediction history!

This project analyzes and predicts apartment rental prices in Manhattan using machine learning techniques. The dataset is sourced from StreetEasy and contains various features about rental listings, such as the number of bedrooms, bathrooms, square footage, amenities, and proximity to the subway.

Calculate the bias of k-fold cross-validation with hyper-parameter configuration

K Nearest Neighbours in Python

Exploring a music dataset by examining correlations between numerical variables, running a principal component analysis for dimensionality reduction and finally fitting both scikit learn Decision Tree Classification and Logistic Regression models to compare their performance.

Project compares three regression models for predicting the amount of gold recovered from gold ore in order to optimize gold production and eliminate unprofitable parameters. Data provided by Zyfra.

A production-ready Email Spam Classifier built using Machine Learning and Natural Language Processing (NLP). This project classifies emails as Spam or Not Spam (Ham) using a clean, modular, and testable codebase.

Machine learning model which can predict the strength of a mixture for given composition of ingredients like cement, slag, ash, water, superplastic, coarse aggregates, fine aggregates, age.