Smart Dine - Restaurant Forecasting Website

Introduction

Smart Dine addresses the critical issue of food waste in the restaurant industry, caused by inefficient inventory management and poor demand forecasting. Restaurants often face financial losses and sustainability challenges due to overstocking and spoilage. Leveraging AI, Smart Dine provides data-driven solutions to optimize inventory levels, reduce food waste, and enhance customer satisfaction.

Key Features

  • AI Demand Prediction: Machine learning models analyze transaction patterns, seasonal trends, and other variables to forecast customer demand and inventory needs.
  • User-Friendly Dashboard: Provides real-time insights and data visualization for better decision-making.
  • Inventory Optimization: Minimizes overstocking and stockouts by aligning inventory with predicted demand.
  • Comprehensive Safety Features: Ensures data privacy and security with features like two-factor authentication.

Development and Innovation

Smart Dine employs advanced technologies, including machine learning models like Random Forest and Neural Networks, to deliver precise demand predictions. A responsive web interface, built using React and PostgreSQL, ensures seamless interaction and data storage. Synthetic data was initially used for model training, with plans to incorporate real-world data from restaurants to enhance accuracy. The system also integrates visualization tools like Matplotlib for effective data representation.

Impact and Future Directions

Smart Dine aims to transform restaurant operations by reducing food waste, cutting costs, and improving customer experiences. Future developments include transitioning to real-world data, integrating with POS systems for real-time data collection, and expanding machine learning capabilities to incorporate complex factors like weather and local events. The platform’s scalability and SQL-based database management will further enhance its usability across diverse restaurant sizes and types, paving the way for widespread adoption in the industry.

Researcher
Sippapas Pronanun
Student
CMKL University
Saritwatt Khanthakamolmart
Student
CMKL University
Jirapat Kulruchakorn
Student
CMKL University
Surawin Sae-kow
Student
CMKL University
Advisor
Dr.Pasin Manurangsi
Adjunct Faculty Member
CMKL University