AA-forecast: anomaly-aware forecast for extreme events

Farhangi, Ashkan; Bian, Jiang; Huang, Arthur; Xiong, Haoyi; Wang, Jun; Guo, Zhishan

doi:10.1007/s10618-023-00919-7

Cited by 2 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We revisit the problem of building machine learning algorithms that involve interactions between entities, such as those between users and items in a recommendation system, or between financial assets in an actively managed portfolio, or between populations in different counties in a diseasespreading process. Our proposed forecasting model uses information available up to time t to predict y t+1,i , the future behavior of entity i at time t + 1 (e.g., the future price of stock i at time t + 1), for a total number of d entities (Laptev et al 2017;Farhangi et al 2022). Designing such models has proven remarkably difficult, as one needs to circumvent two main challenges that require often incompatible solutions.…”

Section: Introductionmentioning

confidence: 99%

Symphony in the Latent Space: Provably Integrating High-Dimensional Techniques with Non-linear Machine Learning Models

Liu

et al. 2023

AAAI

View full text Add to dashboard Cite

This paper revisits building machine learning algorithms that involve interactions between entities, such as those between financial assets in an actively managed portfolio, or interactions between users in a social network. Our goal is to forecast the future evolution of ensembles of multivariate time series in such applications (e.g., the future return of a financial asset or the future popularity of a Twitter account). Designing ML algorithms for such systems requires addressing the challenges of high-dimensional interactions and non-linearity. Existing approaches usually adopt an ad-hoc approach to integrating high-dimensional techniques into non-linear models and recent studies have shown these approaches have questionable efficacy in time-evolving interacting systems. To this end, we propose a novel framework, which we dub as the additive influence model. Under our modeling assumption, we show that it is possible to decouple the learning of high-dimensional interactions from the learning of non-linear feature interactions. To learn the high-dimensional interactions, we leverage kernel-based techniques, with provable guarantees, to embed the entities in a low-dimensional latent space. To learn the non-linear feature-response interactions, we generalize prominent machine learning techniques, including designing a new statistically sound non-parametric method and an ensemble learning algorithm optimized for vector regressions. Extensive experiments on two common applications demonstrate that our new algorithms deliver significantly stronger forecasting power compared to standard and recently proposed methods.

show abstract

Section: Introductionmentioning

confidence: 99%