Download PDFOpen PDF in browser

Leveraging Machine Learning to Improve Demand Forecasting for Production Planning and Inventory Optimization.

EasyChair Preprint no. 13424

20 pagesDate: May 23, 2024

Abstract

Demand forecasting is crucial in production planning and inventory optimization, enabling businesses to align their operations with customer demand. Traditional forecasting methods often struggle to capture the complexity and dynamics of demand patterns, leading to suboptimal production decisions and inventory management. However, the emergence of machine learning techniques presents a transformative opportunity to enhance demand forecasting accuracy and efficiency. This abstract provides an overview of leveraging machine learning to improve demand forecasting for production planning and inventory optimization.

 

The process begins with data collection and preprocessing, where various data sources such as historical sales data, market trends, and customer behavior are gathered and prepared for analysis. Next, the collected data selects and trains suitable machine learning models. Model selection involves considering factors such as data characteristics and forecasting objectives, while training and validation processes ensure the model's performance.

 

Feature selection and extraction techniques are employed to identify relevant demand drivers and improve model performance. Additionally, external data sources, such as social media or weather data, can be incorporated for a more comprehensive understanding of demand patterns.

Keyphrases: Continuous Improvement, data monitoring, Demand Forecasting, Inventory Optimization, monitoring, performance metrics

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@Booklet{EasyChair:13424,
  author = {Edwin Frank},
  title = {Leveraging Machine Learning to Improve Demand Forecasting for Production Planning and Inventory Optimization.},
  howpublished = {EasyChair Preprint no. 13424},

  year = {EasyChair, 2024}}
Download PDFOpen PDF in browser