This project uses Long Short-Term Memory (LSTM) networks to forecast PM2.5 pollution levels based on environmental factors like temperature, humidity, pressure, wind speed, snow, and rain. It employs multivariate time series data, data preprocessing (normalization and sequence creation), and model training to predict future pollution levels.

Python Analysis: A/B, e-commerce, test results determining if this organization should implement a new website and/or maintain their current website

Utilized exploratory data analysis (EDA) to inform data inspection, cleaning, and validation.

Developed a machine learning model to predict the prices of Rolex watches based on various factors such as model, material, year, and market trends. Utilized regression techniques, data preprocessing, and feature engineering to enhance prediction accuracy. Implemented the project using Python, Pandas, NumPy, and Scikit-learn.