Food Expiry Prediction

CNN and Random Forest models that estimate when food will spoil

Predicting when fruit, vegetables and packaged food will expire, to cut food waste. A CNN judges freshness from photographs, while Random Forest and MLP models weigh temperature, humidity and how long the food has been stored.

The aim

Predict when food items, such as fruit, vegetables and packaged goods, will expire, to cut food waste. The project’s full title is Leveraging CNN and Random Forest for Accurate Food Expiry Prediction.

How it works

Images. A convolutional neural network analyses photographs for freshness.
Conditions. Random Forest and multi-layer perceptron models process environmental metadata: temperature, humidity and storage duration.

Data

Built on the Kaggle dataset Fruits Fresh and Rotten for Classification, alongside self-generated features such as days since purchase, to improve generalisation.