Background Banner Image

21 Day Sustainability Challenge

In 21 days, can machine learning recommend ways to reduce your food waste? Put us to the test.

Get Started

what is decision intelligence

We’d like to help you, free of charge!

You shouldn’t have to chose between profits and being kind to our planet. At Peak, we believe a balance of both are possible through AI/ML. That’s why we’ve teamed up with AWS to offer the 21 Day Sustainability Challenge using Amazon Forecast and CODI, Peak’s connected Decision Intelligence system. Want to see if we can help you and your business?

How can this help you?

The 21 Day Sustainability Challenge is designed to show how AI-driven demand forecasting can drive more accurate predictions and recommend ways to reduce food waste, and therefore your carbon footprint. For 21 days, we will run Amazon Forecast on your data to power food waste reduction recommendations. Some of the major benefits are…

  • Reduce Food Waste

    Throw away less food by more accurately supplying a more accurate prediction of demand.

  • Sustainable Business

    Global food waste accounts for 8-10% of all greenhouse gasses – that's more than commercial flights!

  • Reduce Investment

    When you can more accurately predict demand, you can buy less. Who knew reducing inventory and investment could be so green?

  • Fulfil Demand

    Reducing food waste doesn't have to mean out of stock items and unhappy customers. Know exactly how much to supply where to fill their bellies and your pockets.

More opportunities to get green

Reducing food waste isn't the only way businesses can get more sustainable using AI/ML. If food isn't your jam (forgive the pun), contact us about other ways we could help your business save the planet, including:

  • Transport route optimization
  • Waste reduction
  • Water use reduction
  • Power reduction

Next steps

We’ve outlined each step of this process below. Once you have contacted us via our form at the bottom of this page, we will:


Set up a quick call

We’ll quickly assess your needs and confirm whether we can help.


Explain what’s possible

After speaking with you to better understand what you’re trying to achieve, we’ll send you a scope of work.


Upload your data

We’ll send over a mutual NDA and a secure data link, so you can upload the data we require access to


Run Amazon Forecast on Peak

We’ll send over a mutual NDA and secure a data link. We only need access to what’s required to run the test and are ISO 27001 accredited.


Playback the results after 21 days

You’ll receive a customized report containing our findings, and we’ll schedule a video call to walk you through the results and address any questions.


Delete your data

Your business’ data will be removed from our AWS cloud infrastructure once you instruct us to do so. None of your data will remain with us.


We have pulled together some FAQs on our 21 Day Sustainability Challenge that will quickly answer your burning questions. If your question isn't below, just get in touch – we'll get an expert on the phone to you in no time.

What will the report tell me? Will someone explain the results and answer any questions?

The report will confirm how confident we are at predicting demand in your business. We will then translate that into how much food wastage, and therefore CO2 we think you could save by using AI. We will provide confidence levels and aim to evidence a couple of examples to further support our results. <br\> Yes, we’ll set up a call with you to walk you through the results. A Peak data scientist will be available on the call to discuss the results in detail.

How much effort will this be for me?

Besides joining some calls to ensure we're on the right track and sharing your data, you don't need to do anything! Kick up your heels and relax. We'll do the heavy lifting.

How much data do I need to submit? Does it need to be in a certain format?

A minimum of 12 months of historical data at a product/SKU level will allow us to confidently run it through Amazon Forecast. <br\> It’s not essential but in order for us to return our results within 21 days we’d need to receive a target time series data set. This data type defines the target field that you want to generate forecasts for. For example, if you want to forecast the sales for a set of products, then you must create a dataset of historical time-series data for each of the products that you want to forecast. We can provide the details of the mandatory data fields upon request or during our initial call.

What sort of forecasting algorithms will be used on my data?

Amazon Forecast uses AutoML(Automated Machine Learning) which automates complex machine learning tasks, such as algorithm selection, hyperparameter tuning, iterative modelling, and model assessment. It evaluates and compares the forecast output of multiple algorithms, and chooses the best one based on the prediction accuracy per datasets.

What are the other ways AI/ML can make my business more sustainable? Is it only about food waste reduction?

Food waste reduction is just one of the ways AI/ML can make your business more sustainable. We have worked on other projects including truck journey route optimizations, other types of waste reductions, water usage, and more. Talk to us about your sustainability goals and we'll work with you on the art of the possible.