This demo accompanies the tech talk "Building Intelligent Applications with ML.NET", where we explore how to use Matrix Factorization to build a product recommendation system based on co-purchase behavior.

Imagine you're running an e-commerce platform. You have customer purchase data and want to recommend products that are frequently bought together — even if the user hasn't seen them before.

This solution uses:

• ML.NET’s MatrixFactorizationTrainer
• A small sample dataset of user_id, product_id, and Label

• Basics of Matrix Factorization for collaborative filtering
• How to implement recommendations in ML.NET
• Training a model using implicit purchase data
• Making product predictions for a given customer

• .NET 8 SDK
• Visual Studio or VS Code
• ML.NET NuGet Package:

dotnet add package Microsoft.ML

1. Clone or download the repo.
2. Open the folder in Visual Studio or run via CLI.
3. Make sure the dataset amazon.csv is in the Data/ folder.
4. Run the program:

dotnet run

• 🔹 Product Recommendation - Matrix Factorization Problem Sample
• 🎬 Movie Recommendation - Matrix Factorization Sample 1 (Program.cs)
• 🎬 Movie Recommendation - Matrix Factorization Sample 2

• 📄 What is ML.NET and How Does It Work?
• ⚙️ What is Automated Machine Learning (AutoML)?
• 🛠️ ML.NET AutoML Model Builder (Step-by-Step Walkthrough)
• 🚀 Deploy a Model in an ASP.NET Core Web API

• 🛒 Amazon Sales Dataset (Kaggle)
• 📑 Machine Learning at Microsoft with ML.NET (Research Paper)

• 🌐 Open Neural Network Exchange (ONNX)
• 🏢 Artificial Intelligence & ML Customer Showcase (Microsoft)