Solving 3 business problems in 45 minutes using ML.NET

on YouTube ↗39m

" summary

Shows concrete ML.NET recipes: linear regression for taxi/fare and bike demand, matrix factorization recommender that runs offline and yields 27% sales uplift, and unsupervised clustering for customer segments. Demonstrates data cleaning, categorical encoding, normalization, training pipelines, and weekly retrain via CI/CD; claims working systems built with about 20 lines of code for core logic. Notes ML.NET lacks native neural nets but accepts ONNX/TensorFlow imports and offers automated model selection (AutoML).

AI-written summary · about

" chapters (7)

1. 0:00Start
2. 2:09Artificial Intelligence is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and animals. (..) The term is used to describe machines that mimic 'cognitive functions that humans associate with other human minds, such as "learning and problem solving". - Wikipedia
3. 3:55study of algorithms and statistical models that computer systems use in order to perform a specific task effectively without using explicit instructions, relying on patterns and inference instead. - Wikipedia
4. 7:09_unsupervised learning
5. 8:22linear regression how it works
6. 32:35customer segmentation
7. 33:41demand prediction

" related talks

• 42mSolving 3 business problems with ML.NET in 45 minutesMichał Łusiak · Build Stuff 2020
• 56mMachine Learning for .NET developersOlia Gavrysh · NDC Oslo 2020
• 01h 03mMachine learning for C# developers: Introducing MLJeff Prosise · DotNext 2019 Moscow
• 45mMachine Learning for .NET developersOlia Gavrysh · NDC London 2020
• 52mML.NET - Machine Learning made for .NETPeter Drougge · Update Conference Prague 2018
• 01h 04mIntroduction to ML.NETJohn Alexander · NDC Sydney 2018
• 59mMachine Learning in .NET (ML.NET)Agatha Stena · .NET Conf 2018
• 50mA Pragmatic Deep Dive into ML.NETDiederik Krols · Update Conference Prague 2019