Machine learning to help the hospitality industry recover through optimised food production

机器学习通过优化食品生产帮助酒店业复苏

• 批准号: 77521
• 金额: $ 20.39万
• 依托单位: WINNOW SOLUTIONS LIMITED
• 依托单位国家: 英国
• 项目类别: Collaborative R&D
• 财政年份: 2020
• 资助国家: 英国
• 起止时间: 2020 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=77521
• 关键词: Machine; learning; help; hospitality; industry

The global hospitality industry does not have a tool that can accurately help it predict how much food to produce, and when. This results in both economic and environmental challenges. Overproduction of food leads to vast costs; in the UK Hospitality and Food Service Sector, food waste was estimated at over £2.5bn in 2011, with 75% of it recorded as avoidable. The environmental impact is monumental; if global food waste were a country, it would be the third largest emitter of greenhouse gases after the USA & China. Overproduction also lowers food quality. Underproduction causes its own issues; hurting customer satisfaction and margins. Providing chefs with a tool which can give them actionable insights based on a wide range of data including weather patterns, historic waste, time of day and demographic of customers could help them optimise their production. This project aims to build on WSL's experience of building machine learning models and presenting actionable data to chefs in around 1500 kitchens to build a prototype production planning tool which can be presented to customers for feedback. This project's timing is imperative; the hospitality industry has been one of the hardest hit by COVID-19, and needs tools to help it have greater control over operations and margins.

全球酒店业没有一种工具可以准确地帮助它预测生产多少食物，以及何时生产。这导致了经济和环境挑战。食品生产过剩导致巨大的成本;在英国酒店和食品服务部门，2011年的食品浪费估计超过25亿英镑，其中75%是可以避免的。环境影响是巨大的;如果全球食物浪费是一个国家，它将是仅次于美国和中国的第三大温室气体排放国。生产过剩也会降低食品质量。生产不足导致其自身的问题;损害客户满意度和利润率。为厨师提供一种工具，可以根据天气模式、历史废弃物、一天中的时间和客户人口统计等广泛数据，为他们提供可操作的见解，这可以帮助他们优化生产。该项目旨在利用WSL在构建机器学习模型和向大约1500个厨房的厨师提供可操作数据方面的经验，构建一个原型生产计划工具，可以向客户提供反馈。该项目的时机至关重要;酒店业是受COVID-19影响最严重的行业之一，需要工具来帮助其更好地控制运营和利润率。