forecasts the daily number of hospital inpatients for the next 14 days

This project focuses on Supply Chain Analytics and Demand Forecasting using advanced analytics and models to optimize operations and predict future demand.

Energy Forecast Benchmark Toolkit is a Python project that aims to provide common tools to benchmark forecast models.

Time-Series Work Summary in CS Top Conferences (NIPS, ICML, ICLR, KDD, AAAI, WWW, IJCAI, CIKM, ICDM, ICDE, etc.)

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).

Software solution for calculating optimal inventory levels, including lot size and reorder point, using cost data and demand distribution.

Demand Forecasts at Scale

SKU-level customer demand forecasts for SSDs for improved long-term supply planning

A simple application that demonstrates the power of PredictHQ's APIs.

The "Sales Demand Forecasting Regression Model" project aims to develop a predictive model that forecasts future sales demand based on historical data and relevant influencing factors. The project follows a structured approach, encompassing data collection, preprocessing, model selection, training, evaluation, and deployment.

Machine Learning CAISO electric demand forecast using https://github.com/romilan24/load-weather-dataset

This Jupyter Notebook implements Bayesian modeling techniques to fit a posterior distribution and forecast demand for an e-commerce company.

Evaluating tree-based approaches for timeseries

This project is based on supply chain analytics along with demand forecasting and inventory management of the top selling product. Demand forecasting is done by using the prophet time series model. Also, the dashboard consists of all the important insights related to customers, products, orders as well as the forecasting outcomes.

Forecasted product sales using time series models such as Holt-Winters, SARIMA and causal methods, e.g. Regression. Evaluated performance of models using forecasting metrics such as, MAE, RMSE, MAPE and concluded that Linear Regression model produced the best MAPE in comparison to other models

The goal of the project is to utilize Recurrent Neural network model (biLSTM) to forecast demand of bike rentals using seasonal and exogenous features

Full-stack Highly Scalable Cloud-native Machine Learning system for demand forecasting with realtime data streaming, inference, retraining loop, and more

The Travel Market Simulator project aims at providing reference implementation, mainly in C++, of a travel market simulator.

C++ Simulation Travel Demand Generation Library

C++ Simulation Discrete Event Management Library