[Day 194] Using Video Generation Models for Taxi OD Demand Matrix Prediction

 Hello :)
Today is Day 194!


A quick summary of today:
  • I finished the paper for which I read many papers and posted them throughout May/June/July



Since May I have been talking about reading research related to predicting OD demand matrix using either graph neural networks or next-frame (video) prediction models. Well fast forward to today ~ and I finished it. Everything is on my github repo.

I ran data through 3 models: historical average, ConvLSTM, PredRNN - HA the most common baseline, and ConvLSTM and PredRNN - two of the best next-frame prediction models.

Here is the abstract of the paper:

Predicting taxi demand is essential for managing urban transportation effectively. This study explores the application of next-frame prediction models—ConvLSTM and PredRNN—to forecast Origin-Destination (OD) taxi demand matrices using a concatenated dataset of NYC taxi data from early 2024. ConvLSTM achieved an RMSE of 1.27 with longer training times, while PredRNN achieved 1.59 with faster training. These models offer alternatives to traditional graph-based methods, showing strengths and trade-offs in real-world scenarios. Additionally, an open-source framework for model deployment is introduced, aiming to bridge the gap between research and practical implementation in taxi demand forecasting.


Keywords: Taxi, Demand, forecasting, OD Matrix, Next-Frame Prediction Models

The training was tidious ... I am on a mac so it was very slow to train models on MPS. For the future I need to look into other next-frame prediction models and include them in the comparison. 

The results at the moment are:

Some example predictions:


The full paper is in the repository - paper.pdf.

Hopefully I get to develop this further, but for now I am happy I got to read so many papers on a specific topic. I learned a lot about graph neural networks, next-frame prediction models, and specifically their application in traffic forecasting and demand. Such models are transferrable to other topics so I am glad I did this research and wrote a small paper. 


That is all for today!

See you tomorrow :)

Popular posts from this blog

[Day 198] Transactions Data Streaming Pipeline Porject [v1 completed]

Image
 Hello :) Today is Day 198! A quick summary of today: data streaming pipeline project [v1 done] Here is a link to the project's repo. Well ... I did not know I can do it in a day (~14 hours) after yesterday's issues but here we are. Turns out in order to insert the full (~70 variables with nested/list structure), I need the proper pyspark schema. And yesterday I did not have that and that is why when I was reading data in the kafka producer I was getting NULL in the columns - my schema was wrong. Well today I not only fixed the schema for the 4 variables I had yesterday, but included *all* the variables that come from the Stripe API ~ 70 (for completeness).  When I run docker-compose, the data streams and is input into the postgres db (and is still running). Unfortunately, the free Stripe API for creating realistic transactions has a limit of 25, so every 3 seconds, 25 new transactions are sent to the db. It has been running half the day (since I got that set up) and as I am wr
Read more

[Day 107] Transforming natural language to charts

Image
 Hello :) Today is Day 107! A quick summary of today: created text2chart - transforming natural language to charts [ github ] [ webapp ] I am super sick, but in the around 3 hours of my fever not being high, I managed to study a bit. I was again thinking about creating some nlp project but was stuck on the idea of how to host a model. After looking around I found this article where they create a similar app called chat2vis  and they use codellama. I know codellama is an open source model that I can get from huggingface and I wondered, how did they host it. Turns out - they ask the user to input a huggingface api key, which then allows for querying and generating content. (AWESOME! this is applicable to some of the other PDF chat apps that I have, but I will look to make an app of them later).  My fever eased a bit, and I sat on my chair to do some work ^^ Here is a breakdown of the app. I used streamlit. Also, 2 default datasets during dev: Financial Statements of Major Companies(2009-
Read more

[Day 54] I became a backprop ninja! (woohoo)

Image
 Hello :) Today is Day 54! A quick summary of today: Read through cs231n's neural network lectures [1] [2] [3] Spent 8 hours going over Andrej Karpathy's backprop ninja tutorial After yesterday's confidence boost in doing backprop, I came in today with the intention of becoming of, as Andrej Karpathy calls it, a backprop ninja.  The cs231n NN lectures were the usual about how NN became to be, param initialization, activation functions, loss functions, regularization and optimizers. Nothing out of the ordinary, but still was good to reassure myself of that knowledge. But that was definitely not the main even of today. As I mentioned, I wanted to become (or at least attempt to become) a backprop ninja today. I have watched that particular tutorial twice, the 1st time I had no idea what is going on, the 2nd time I could follow, and now it was the 3rd time - and now, I wanted to participate and actually see the why and the how of the things we have to do, when we do manual back
Read more