Rusty Bargain is a used car buying and selling company that is developing an app to attract new buyers. My job as data science is to create a model that can determine the market value of a car.

Honors Thesis Research

Creating a ML-model that forecasts the price of a car (historic data)

Machine Learning model for price prediction using an ensemble of four different regression methods.

Compare ticket price and distance between car, train and bus + Price prediction + dynamic visualization

My capstone project for the Institute of Data investigates the metadata of songs on Spotify, building a predictive model to project a track's popularity on Spotify using its audio features.

Learning gradient boosting algorithms

This represents the car's price predictor based on LightGBM + Optuna. The final goal is to use it to predict my father's car price.

DS & ML Bootcamp Final Team Project

It is the detailed collection of house listings from various cities and regions in Bangladesh, with a specific focus on Dhaka and Chittagong. It encompasses essential details such as location, property type, size, amenities, and pricing.

Simple service that predicts car price based on its characteristics

Customers knowledge, supply chain movement and sales forecasting, Customer Lifetime value, churn and survival analysis

Analytic Vidhya's Problem Statement to Predict or Forecast the Future Energy Demand For Next Three Years.

l train and evaluate multiple time-series forecasting models using the Store Item Demand Forecasting Challenge dataset from Kaggle. This dataset has 10 different stores and each store has 50 items, i.e. total of 500 daily level time series data for five years (2013–2017).

This is an Income prediction model pitched in for a Kaggle competition that trains on preprocessed data using LGBMRegressor and helps predict income.

Predicting building energy consumption as part of the WiDS 2022 Datathon

House-Prices Advanced Regression Techniques Competition Solution

Prediction of the sale price of a vehicle using predictive models using gradient boosting