MQTransformer: Multi-Horizon Forecasts with Context Dependent and Feedback-Aware Attention

Eisenach, Carson; Patel, Yagna; Madeka, Dhruv

doi:10.48550/arxiv.2009.14799

Cited by 5 publications

(13 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the selected features are the same for all these methods, we believe the lower SD is due to the dynamic dropout probability mechanism in DemandNet's prediction model. Overall, the two proposed models, DemandNet-LSTM and DemandNet-GRU, consistently outperform the baseline NN models [20,19], especially under longer horizon windows (40 and 80 days) due to their ability to incorporate state closure/open policy in their prediction. Considering all three evaluation metrics, DemandNet-GRU is best suited for the US consumer spending dataset due to reported higher confidence and accuracy.…”

Section: Resultsmentioning

confidence: 93%

See 1 more Smart Citation

A Novel Deep Learning Model for Hotel Demand and Revenue Prediction amid COVID-19

Farhangi,

Huang,

Guo

2022

Preprint

View full text Add to dashboard Cite

The COVID-19 pandemic has cast a substantial impact on the tourism and hospitality sector. Public policies such as travel restrictions and stay-at-home orders had significantly affected tourist activities and service businesses' operations and profitability. To this end, it is essential to develop an interpretable forecast model that supports managerial and organizational decision-making. We developed DemandNet, a novel deep learning framework for predicting time series data under the influence of the COVID-19 pandemic. The framework starts by selecting the top static and dynamic features embedded in the time series data. Then, it includes a nonlinear model which can provide interpretable insight into the previously seen data. Lastly, a prediction model is developed to leverage the above characteristics to make robust long-term forecasts. We evaluated the framework using daily hotel demand and revenue data from eight cities in the US. Our findings reveal that DemandNet outperforms the state-of-art models and can accurately predict the impact of the COVID-19 pandemic on hotel demand and revenues 1 .

show abstract

Section: Resultsmentioning

confidence: 93%

“…• MQ-Transformer [20]: A transformer-based deep learning model that benefits from static features and future predefined labels. It also provides a state-of-art prediction in multiple datasets.…”

Section: Methods For Comparisonmentioning

confidence: 99%

A Novel Deep Learning Model for Hotel Demand and Revenue Prediction amid COVID-19

Farhangi,

Huang,

Guo

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…This is typically achieved by two avenues. The first approach, including Salinas et al (2020Salinas et al ( , 2019 Eisenach et al (2022). Other classes of works include variance reduced training (Lu et al, 2021) or domain adaptaton based techniques (Jin et al, 2022).…”

Section: Related Workmentioning

confidence: 99%

Robust Probabilistic Time Series Forecasting

Yoon¹,

Park²,

Ryu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Probabilistic time series forecasting has played critical role in decision-making processes due to its capability to quantify uncertainties. Deep forecasting models, however, could be prone to input perturbations, and the notion of such perturbations, together with that of robustness, has not even been completely established in the regime of probabilistic forecasting. In this work, we propose a framework for robust probabilistic time series forecasting. First, we generalize the concept of adversarial input perturbations, based on which we formulate the concept of robustness in terms of bounded Wasserstein deviation. Then we extend the randomized smoothing technique to attain robust probabilistic forecasters with theoretical robustness certificates against certain classes of adversarial perturbations. Lastly, extensive experiments demonstrate that our methods are empirically effective in enhancing the forecast quality under additive adversarial attacks and forecast consistency under supplement of noisy observations. The code for our experiments is available at https://github.com/tetrzim/ robust-probabilistic-forecasting.

show abstract

“…Fortunately, quantile regression [14,13], which has been successfully used for robustly modeling probabilistic outputs, comes to rescue. The incorporation of the quantile regression component to various sequential neural network backbones has been shown to be particularly effective with recent advances in deep learning [29,9,18,6]. Obtaining a full probabilistic prediction (i.e., the ability to query a forecast at an arbitrary quantile) usually requires generating multiple quantiles at once.…”

Section: Introductionmentioning

confidence: 99%

Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting

Park¹,

Maddix²,

Aubet³

et al. 2021

Preprint

View full text Add to dashboard Cite

Quantile regression is an effective technique to quantify uncertainty, fit challenging underlying distributions, and often provide full probabilistic predictions through joint learnings over multiple quantile levels. A common drawback of these joint quantile regressions, however, is quantile crossing, which violates the desirable monotone property of the conditional quantile function. In this work, we propose the Incremental (Spline) Quantile Functions I(S)QF, a flexible and efficient distribution-free quantile estimation framework that resolves quantile crossing with a simple neural network layer. Moreover, I(S)QF inter/extrapolate to predict arbitrary quantile levels that differ from the underlying training ones. Equipped with the analytical evaluation of the continuous ranked probability score of I(S)QF representations, we apply our methods to NN-based times series forecasting cases, where the savings of the expensive re-training costs for non-trained quantile levels is particularly significant. We also provide a generalization error analysis of our proposed approaches under the sequence-tosequence setting. Lastly, extensive experiments demonstrate the improvement of consistency and accuracy errors over other baselines.

show abstract

MQTransformer: Multi-Horizon Forecasts with Context Dependent and Feedback-Aware Attention

Cited by 5 publications

References 18 publications

A Novel Deep Learning Model for Hotel Demand and Revenue Prediction amid COVID-19

A Novel Deep Learning Model for Hotel Demand and Revenue Prediction amid COVID-19

Robust Probabilistic Time Series Forecasting

Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting

Contact Info

Product

Resources

About