Diffusion-aware Censored Gaussian Processes for Demand Modelling

Authors: Filipe Rodrigues

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental This paper proposes Diffusion-aware Censored Demand Models, which combine a Tobit likelihood with a graph-based diffusion process in order to model the latent process of transfer of unsatisfied demand between similar products or services. We instantiate this new class of models under the framework of GPs and, based on both simulated and real-world data for modeling sales, bike-sharing demand, and EV charging demand, demonstrate its ability to better recover the true demand and produce more accurate out-of-sample predictions.
Researcher Affiliation Academia Filipe Rodrigues Technical University of Denmark EMAIL
Pseudocode No The paper describes the methodology using mathematical equations and textual explanations, but it does not include any explicitly labeled pseudocode blocks or algorithms.
Open Source Code Yes Source code for all the experiments is provided at: https://bit.ly/3E2kdSJ
Open Datasets Yes We now turn to experiments on real-world supermarket vegetable sales data obtained from [Sup]. ... [Sup, 2024] Sup. Supermarket sales data: Sales data of vegetables in supermarket. https://www.kaggle.com/datasets/ yapwh1208/supermarket-sales-data, 2024. Accessed: 2024-04-23.
Dataset Splits Yes We randomly sample 90% observations for training and leave 10% for testing. ... We hold out 30% of data for testing.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU, GPU models, memory amounts) used for running the experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., programming languages, libraries, or solver versions) used in the experiments.
Experiment Setup Yes The hyper-parameters of the likelihood in Eq. 9 are then: the observation variance σ2, the diffusion lengthscale ℓdiff, the sink node parameter πdiff, and the number of diffusion steps Ndiff. ... for Datasets A and C, the best results were obtained with a fixed ℓdiff = 1, while for Dataset B learning ℓdiff resulted in slightly better results. ... We simulate the censoring process using a 2-state Markov model... with fixed diffusion parameters and with a sink node probability of 20%.