7.4. Case Study Example (Optional)

Project: Reducing Food Wastage in School Canteens

In this project, the main goal is to reduce the amount of food that goes to waste in school canteens. This is important because reducing food waste can help save money, decrease environmental impact, and ensure that students receive the meals they need without excess leftovers.

Imagine you're at a birthday party where too much cake is made. If everyone eats just a slice, there will be a lot of leftover cake that might get thrown away. Similarly, schools can make too much food that students don’t eat, leading to waste.

1. Problem Scoping: Identify that canteens overproduce meals.

The first step in the AI Project Cycle involves defining the issue clearly. In this case, the school canteens are making more meals than what students actually consume, leading to unnecessary food waste. Understanding this helps in developing a specific plan to address the issue.

Think about when you plan a family dinner. If you make too much food without knowing how many people will come, you might end up with a lot of leftovers. Here, identifying the problem helps us figure out how to serve just the right amount.

2. Data Acquisition: Collect data on student attendance, meal preferences.

Once the problem is identified, the next step is to gather relevant data. This involves collecting information about how many students are attending school on different days and what meals they prefer. This data is crucial for making informed decisions about meal preparation.

Imagine a popular restaurant wanting to know what dishes to prepare. They might check past orders to see which meals were favorites. Similarly, schools can look at attendance and meal choices to know how many meals to prepare.

3. Data Exploration: Analyze patterns in leftover food and attendance.

In this phase, the collected data is analyzed to discover trends. Schools would look at how much food is left over on each day compared to student attendance. Understanding these patterns can reveal specific times or days when food waste is highest, which can help in adjusting meal production.

Consider a gardener who tracks how many flowers bloom each season. By looking at the data, they can see which types thrive and which don’t. In the same way, analyzing food waste patterns helps schools see where they can improve meal planning.

4. Modelling: Build a predictive model to estimate the number of meals needed.

At this stage, an AI model is developed using the analyzed data. This model predicts the number of meals required based on factors like student attendance and preferences. By training the model with historical data, it can better estimate meal quantities for future days.

Imagine if you had a magic machine that told you exactly how many slices of pizza to order for a party based on past parties. By learning from each event, the machine gets better and better at predicting the right amount. This is what the AI model does for the canteen.

5. Evaluation: Validate accuracy of meal prediction vs. actual wastage.

The final step involves testing how well the AI model performs its predictions. This means comparing the estimated number of meals needed to the actual leftovers. If the model predicts accurately, it will help reduce food wastage significantly over time.

Think of a weather forecast. If the forecast predicts sunny weather and it turns out to be correct, we can rely on it for our plans. Similarly, evaluating the AI model ensures it reliably estimates meal requirements.

--