Code repository for the online course "Feature Engineering for Time Series Forecasting".

The official code for "TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting (ICLR 2024)". TEMPO is one of the very first open source Time Series Foundation Models for forecasting task v1.0 version.

Learn about Probabilistic Time Series Forecasting, its key techniques, real-world applications, and advantages over traditional forecasting methods.

Hierarchical Time Series Forecasting

No description provided.

Forecasting Time Series with Moving Average and Exponential Smoothing

Analysis Sales data to gain insights and create Interactive Sales Dashboard and also predict /Forecast the next sales with the use of Power-Bi.

Automatically select DNNs for time series forecasting under consideration of complexity and resource consumption.

Official repo for the following paper: Traffic Forecasting on New Roads Unseen in the Training Data Using Spatial Contrastive Pre-Training (SCPT) (ECML PKDD DAMI '23)

Solar Irradiance Forecasting Using Deep Learning Techniques

Dhaka weather forecasting model trained using API from Open-Meteo.com

Investigation of the capabilities of foundations models in the context of time series forecasting

Analyze and propose the plan to monitor and estimate business aspects

data and code associated with the publication "Age structure augments the predictive power of time series for fisheries and conservation" by Tara E. Dolan, Eric P. Palkovacs, Tanya L. Rogers, and Stephan B. Munch.

Time series forecasting on future sales with ARIMA and SARIMAX algorithms

Analyzing retail sales data to craft targeted marketing, elevate customer experiences, and forecast future sales.

This project enhances agricultural weather forecasting by predicting solar radiation (SRAD) using machine learning and deep learning models, including KNN, Random Forest, XGBoost, LSTM, and hybrid methods like Voting and Stacking Regressors.

IoT-Based Smart Energy Meter with Energy Forecasting

In this section, we will use machine learning algorithms to perform time series analysis.

Deep learning model for forecasting the spatiotemporal evolution of fluid-induced microearthquakes

This project aims to analyze and forecast traffic flow using the Seasonal Autoregressive Integrated Moving Average (SARIMA) model. The dataset comprises traffic flow data collected from multiple junctions, with a focus on daily vehicle counts at Junction 1.

Two projects developed as part of a university course on Artificial Neural networks and Deep Learning, in particular, an image classification task, and a univariate time series forecasting task.

Implementing method of Willemain et al., 2004 for forecasting intermittent demand

This project's objective is to leverage the ARIMA time series regression model to accurately forecast future product sales quantity, enhancing predictive capabilities for better planning and decision-making.

Long-term solar activity forecast for solar cycles 25 and 26 with libraries numpy, pandas, scipy, sympy, sklearn. A science project by physics undergrad student.

Learn about how we can use models to make predicitons in the future based on historical data.

Data science project to forecast retail sales from a large grocery chain using a multi-step forecasting Machine Learning algorithm

An Implementation of N-BEATS using Pytorch Lightning

Plotly Dashboard for calibrating WOFOST 7.2

The "Cincinnati Traffic Crashes - Time Series Analysis" is a comprehensive study that employs statistical techniques to examine patterns and trends in traffic accidents over time within the Cincinnati area. This analysis aims to forecast future incidents, and assist in developing strategies to enhance road safety.