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 :)