Data Science materials

Greetings! This repository showcases the continuous assessment for CCT College Dublin's "Machine Learning for Business" course, specifically focusing on the application of machine learning models to time series data. In this project, we applied a total of 8 time series models to gain comprehensive insights into the dataset.

Time Series Analysis. Dataset: UCI repository.

This project focuses on Multivariate Sector Price Prediction using macroeconomic indicators. By leveraging a custom-built LSTM model in PyTorch, we predicted the prices of 10 financial sectors simultaneously. The model takes as input the historical price data of these sectors along with key macroeconomic indicators.

How to use Machine Learning for Time Series Forecasting \ Dataset: Hourly Energy Consumption¶ (Source: Kaggle.com

This project utilizes Prophet, a powerful forecasting tool developed by Facebook, to predict seasonal sales patterns. Leveraging time series analysis techniques, the project aims to forecast the seasons of the year with the highest sales.

This is our final project for Data Science and Applications Course

Store sales forecasting using time series forecasting is a data-driven approach that utilizes historical sales data to predict future sales trends. By analyzing patterns, seasonality, and other temporal factors in the data, businesses can make informed decisions about inventory management, staffing, and marketing strategies.

Se realiza un análisis exploratorio y de predicción de las acciones con fines académicos y de aprendizaje. Se tomaron las acciones de NVIDIA desde 2016 hasta 2024. Los métodos implementados fueron Modelo ARIMA con y sin Rolling para establecere una comparativa con base a los parámetros extraídos por los criterios AIC, BIC y HQIC.

An advanced R script for time-series forecasting with multiple robust methodologies. It enables precise future predictions from historical data.

Forecasting of retail sales data for a brick-and-mortar store. The focus is on exploring time series characteristics, building ARIMA and SARIMAX models, and selecting the optimal model based on AIC and RMSE metrics. The project provides insights into trends, seasonality, and prediction accuracy for business decision-making.