Day 26 – Personalized Book and Movie Recommendations – 30 Day AI Challenge 2024

Welcome to the 2024 Edition of the #30DayAIChallenge. This year, we’ll be focusing on making Generative AI more accessible for all. So follow along and give each challenge a try yourself, plus share your own thoughts and experiments with a community of like-minded learners and tinkerers!*

Week 4’s theme is “Back To The Future: Living With AI“, which takes on an AI infused lifestyle…or everyday AI use cases that can make our lives a little easier or better.

Today’s Challenge: Find The Best Books & Movies With AI

Ever spent more time looking for what to watch on Netflix than actually watching the content? Today, given the vast and seemingly endless sea of content, finding the next book to read or movie to watch can be daunting and time consuming. That’s where AI comes into play, offering a speedy, fun way to get some pretty spot-on and personalized recommendations.

Beginner’s Guide: Off The Shelf Options To Try First

The challenge starts with understanding the basics of how AI recommendation systems work. Many streaming platforms and online bookstores already utilize these technologies to suggest content you might enjoy, based on your past interactions. To get started:

1. Explore AI-based Recommendation Services: Platforms like Netflix, Spotify, and Amazon use complex algorithms to suggest movies, music, and books. Pay attention to how these platforms categorize content and the types of recommendations they offer. Some of these platforms do a better job than others…for example Spotify’s AI DJ does an excellent job of personalizing music recommendations.
2. Use Specific AI Recommendation Apps: There are apps dedicated to book and movie recommendations that you can experiment with. Goodreads for books and Letterboxd for movies are great places to start, as they both offer personalized suggestions based on your ratings and preferences.
3. Understand the Basics: Know that most AI recommendation systems use collaborative filtering, content-based filtering, or a mix of both to suggest content. Collaborative filtering recommends items by finding similar users. Content-based filtering suggests items similar to what you’ve liked before.

Use AI Chatbots For More Personalized Recommendations

Here’s where things get interesting…you can use your favourite AI powered chatbot to get some pretty interesting recommendations. Here’s an older example, from Day 1 of the 2023 #30DayAIChallenge (Movie Recommendations):

30 Days of AI: Unleashing the Possibilities of Artificial Intelligence in Daily Life: Day 1 – Movie Recommendations

The key to getting the best results is (1) picking a chatbot what is adequately trained and up-to-date, or perhaps even connected to the web…here, ChatGPT, Google Gemini, Claude and others are pretty good picks, and (2) providing adequate context to ensure your recommendations are personalized. I’d also recommend iterating and having a conversation, vs just going with the first output (i.e. just talk to the bot as you would a human to get better and more refined recommendations).

Similar to the movie recommendation example above, here’s a very simple way to find very specific book recommendations:

Mini Challenges For You To Try Out

Here are some fun and creative challenges you can try with your favorite AI chatbot to get personalized movie, TV show, and book recommendations:

1. The Mood Matcher Challenge: Describe your current mood or emotions in as much detail as possible to the AI chatbot, and ask for book, movie, or TV show recommendations that match or complement your mood. This can lead to surprisingly apt suggestions that resonate with how you’re feeling.
2. The Decade Dive Challenge: Pick a decade you’re interested in or one that you feel nostalgic about. Ask the chatbot to recommend movies, TV shows, and books that were either set in or released during that decade. It’s a fun way to time-travel through media!
3. The Genre Bender Challenge: Ask for recommendations on books, movies, and TV shows in a genre you’re unfamiliar with or don’t usually prefer. Specify any other genre you typically enjoy to see if the chatbot can find crossover hits or gateway content that might pique your interest in new genres.
4. The Mix-and-Match Challenge: Give the chatbot a mix of elements you’d like to see in a story (e.g., space travel, a romantic subplot, and a mystery to solve). See what movies, TV shows, and books it recommends that contain these elements. This challenge can uncover hidden gems you might not find otherwise.
5. The Character Connection Challenge: Describe a fictional character you love and ask for recommendations on movies, TV shows, and books with similar characters. It’s a great way to find new favorites based on character traits or arcs you already enjoy.
6. The World Builder’s Challenge: Ask for recommendations based on a specific setting or world-building element you enjoy (e.g., dystopian futures, high fantasy realms, or detailed historical settings). This can lead to recommendations that transport you to your favorite kinds of worlds.
7. The Reverse Recommendation Challenge: Start by recommending a movie, TV show, or book you recently enjoyed to the chatbot. Then, ask it to suggest similar content. This can be a neat way to see how well the AI understands your tastes and how it can build upon them.
8. The Random Word Challenge: Give the chatbot a random word or phrase and ask for movie, TV show, or book recommendations based on that word alone. This could result in some of the most unexpected and delightful discoveries.

These challenges should make the process of finding new favorites more engaging…have fun experimenting!

For Advanced Users: AI Personalization On Steroids

If you’re comfortable with the tech, here are a few things you can try out…

1. Experimenting with AI Recommendation Engines: Tools like TensorFlow or PyTorch can be used to build your own recommendation system. Try creating a simple model that recommends books or movies based on a dataset of your preferences.
2. Exploring Niche Databases: Look for databases or APIs that offer raw data on books, movies, and user reviews. This can provide a more hands-on approach to understanding how algorithms make connections between content and user preferences.
3. Personalization and Fine-Tuning: Advanced users can focus on refining the accuracy of recommendations by incorporating more complex data, such as user reviews, detailed preferences, and even the time of day or mood as variables in the recommendation algorithm.

Here’s a great, older example of some of the above, where I downloaded a large database from IMDB, plus also a set of TV shows and movies I had already rated. I then used ChatGPT’s Data Analyst to create my very own database of 32k titles, ranked based on my personal tastes. Now, that should reduce some of that time wasted browsing through Netflix, Amazon Prime or Disney+! 😄

I had ChatGPT build my own Personal Movie Recommendation Engine by analyzing 32k Movies and TV Shows

Closing Thoughts

AI can already help us find books and movies we’ll love, making it easier to discover new favorites that feel like they’re picked just for us. As AI gets better, we can look forward to even smarter systems that know exactly what we like with incredible precision. Give it a try…I know you’ll be impressed!

If you give any of these tools or challenges a try, leave a comment and share your experience! If you’re using other platforms to post, please tag your Facebook, Twitter / X or LinkedIn post with #30DayAIChallenge so others can find it too.

Till tomorrow…

*Please note: Participation in the 30 Day AI Challenge is at your own discretion and responsibility. Always ensure that no sensitive personal information, confidential, or proprietary company data is shared. Adhere to all applicable local laws and company policies. Enjoy exploring AI responsibly!