ML Two
Lecture 10
🤗Recommender system😎 - Movie Recommender
with CreateML

Welcome 👩‍🎤🧑‍🎤👨‍🎤

First of all, don't forget to confirm your attendence on Seats App!

Today's lecture:
-- Introduction to recommendation system 🤑
-- A simple movie recommender

money talks 🤑

money-related AI:
-- recommendation system
-- market price prediction
-- etc.

art work prices prediction

art analytics: artnome

Recommendation System!
(RS)

before talking about what RS is, let's start by examining the data

Training:
Data
Netflix Prize data

There are two entities in RS: user and item (movie)

There is one important quantity of user-item interaction: rating

What does the dataset look like: to organise user, item and ratings together in a dataset we'd use a tabular data format.
(sketch on the whiteboard)

Recommendation system paradigms:
-- content-based: find similar items OR users without using user-item interaction data.
-- collaborative filtering: find similar user-item iteraction history
-- hybrid, etc.

keyword: embedding(aka some sort of represenation of user/item) and similarity
-- more explanations here

Let's do some data pre-processing and training!
all code here 🥰

Hard mode:
open a terminal:

cd to/the/code/folder 

conda create -n RecPrepEnv python=3.6 

conda activate RecPrepEnv 

put "netflix-prize-data" to the same directory as preparation.py (why?)

Hard mode:
open a terminal:

cd to/the/code/folder 

conda create -n RecPrepEnv python=3.6 

conda activate RecPrepEnv 

python preparation.py 

then, a new "netflix-prize-data.csv" will appear in the folder "netflix-prize-data", check it out!

🙌 Hands-on session
1. Open CreateML, set up new project and select "recommendation" template.
2. Drop the "netflix-prize-data.csv" to the training data.
3. Assign users/items/ratings dropdown menu.
4. Click on training!
5. Preview and download the model

Next:
run the training playground to see what the output of the recommender ML model is

Human autonomy issue in recommender system: Lorenz Curve

🙌 Reading session
Let's have a look at a legal framework of AI governance
-- 1. AI Act - a summary and another summary .
-- 2. AI Act - the briefing.

🙌 Reading session
Let's have a look at the UK government response for AI regulation
-- 1. Read through this summary article.
-- 2. Think about one or more sectors/applications that you are interested in, have a glance over the response and think about how those sectors/applications will be impacted.

🎉

Today we talked about:
- 1. Recommendation system: user, item, user-item interaction.
- 2. Movie Recommender as an example.
- 3. Discussions on ethics of recommender system.

A weekly gentle reminder of the final assessment presentation ✌️🥁

We'll see you next week same time same place! 🫡