Large-scale User Visits Understanding and Forecasting with Deep Spatial-Temporal Tensor Factorization Framework

Ma, Xiaoyang; Zhang, Lan; Xu, Lan; Liu, Zhicheng; Chen, Ge; Zhang, Xiao; Wang, Yang; Wu, Zhengtao

doi:10.1145/3292500.3330728

Cited by 12 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, some works integrate decomposition with neural networks (Chen et al 2018;Ma et al 2019;Sun and Chen 2019), like tensor-train decomposition with recurrent neural network (TTRNN) ) can achieve promising As we view the last mode N (N = 2 in this example) of multiple TS as the temporal mode, i.e., I N = T , the last mode duplication matrix…”

Section: Tensor Decomposition-based Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Block Hankel Tensor ARIMA for Multiple Short Time Series Forecasting

Shi

Yin

Cai

et al. 2020

AAAI

View full text Add to dashboard Cite

This work proposes a novel approach for multiple time series forecasting. At first, multi-way delay embedding transform (MDT) is employed to represent time series as low-rank block Hankel tensors (BHT). Then, the higher-order tensors are projected to compressed core tensors by applying Tucker decomposition. At the same time, the generalized tensor Autoregressive Integrated Moving Average (ARIMA) is explicitly used on consecutive core tensors to predict future samples. In this manner, the proposed approach tactically incorporates the unique advantages of MDT tensorization (to exploit mutual correlations) and tensor ARIMA coupled with low-rank Tucker decomposition into a unified framework. This framework exploits the low-rank structure of block Hankel tensors in the embedded space and captures the intrinsic correlations among multiple TS, which thus can improve the forecasting results, especially for multiple short time series. Experiments conducted on three public datasets and two industrial datasets verify that the proposed BHT-ARIMA effectively improves forecasting accuracy and reduces computational cost compared with the state-of-the-art methods.

show abstract

Section: Tensor Decomposition-based Methodsmentioning

confidence: 99%

“…For example, Tucker decomposition integrated with AR model was proposed (Jing et al 2018) to obtain the multilinear orthogonality AR (MOAR) model and the multilinear constrained AR model for high-order TSF. Moreover, some works incorporate decomposition with neural networks for more complex tensorial TS Ma et al 2019).…”

Section: Introductionmentioning

confidence: 99%

Block Hankel Tensor ARIMA for Multiple Short Time Series Forecasting

Shi

Yin

Cai

et al. 2020

AAAI

View full text Add to dashboard Cite

show abstract

“…Optimal Spend Rate Estimation. There are number of works that aim to estimate optimal spend rates for budget pacing [30,2,3,28]. Ma et al [30] and Agarwal et al [2] primarily focus on the on the spend plan estimation.…”

Section: Related Workmentioning

confidence: 99%

“…The temporal effects have led to a variety of work on constructing spend plans for a campaign which learn how to distribute a budget over time [30,2,3,28]. Generally, the approach taken in these works is twofold: first, they use some model (e.g.…”

Section: Introductionmentioning

confidence: 99%

Optimal Spend Rate Estimation and Pacing for Ad Campaigns with Budgets

Kumar¹,

Morgenstern²,

Schrijvers³

2022

Preprint

View full text Add to dashboard Cite

Online ad platforms offer budget management tools for advertisers that aim to maximize the number of conversions given a budget constraint. As the volume of impressions, conversion rates and prices vary over time, these budget management systems learn a spend plan (to find the optimal distribution of budget over time) and run a pacing algorithm which follows the spend plan.This paper considers two models for impressions and competition that varies with time: a) an episodic model which exhibits stationarity in each episode, but each episode can be arbitrarily different from the next, and b) a model where the distributions of prices and values change slowly over time. We present the first learning theoretic guarantees on both the accuracy of spend plans and the resulting end-to-end budget management system. We present four main results: 1) for the episodic setting we give sample complexity bounds for the spend rate prediction problem: given n samples from each episode, with high probability we havewhere ρe is the optimal spend rate for the episode, ρe is the estimate from our algorithm, 2) we extend the algorithm of Balseiro and Gur [12] to operate on varying, approximate spend rates and show that the resulting combined system of optimal spend rate estimation and online pacing algorithm for episodic settings has regret that vanishes in number of historic samples n and the number of rounds T , 3) for non-episodic but slowly-changing distributions we show that the same approach approximates the optimal bidding strategy up to a factor dependent on the rate-of-change of the distributions and 4) we provide experiments showing that our algorithm outperforms both static spend plans and non-pacing across a wide variety of settings.

show abstract

“…In terms of the matrix or tensor decomposition-based ones, Shi et al proposed a strategy that combines low-rank Tucker decomposition into a unified framework [48]. Ma et al proposed a deep spatial-temporal tensor factorization framework, which provides a general design for high-dimensional time-series forecasting [49]. To model the inherent rhythms and seasonality of time-series as global patterns, Chen et al [50] proposed a low-rank autoregressive tensor completion framework to model multivariate time-series' data.…”

Section: Time-series Predictionmentioning

confidence: 99%

Tri-Partition Alphabet-Based State Prediction for Multivariate Time-Series

et al. 2021

View full text Add to dashboard Cite

Recently, predicting multivariate time-series (MTS) has attracted much attention to obtain richer semantics with similar or better performances. In this paper, we propose a tri-partition alphabet-based state (tri-state) prediction method for symbolic MTSs. First, for each variable, the set of all symbols, i.e., alphabets, is divided into strong, medium, and weak using two user-specified thresholds. With the tri-partitioned alphabet, the tri-state takes the form of a matrix. One order contains the whole variables. The other is a feature vector that includes the most likely occurring strong, medium, and weak symbols. Second, a tri-partition strategy based on the deviation degree is proposed. We introduce the piecewise and symbolic aggregate approximation techniques to polymerize and discretize the original MTS. This way, the symbol is stronger and has a bigger deviation. Moreover, most popular numerical or symbolic similarity or distance metrics can be combined. Third, we propose an along–across similarity model to obtain the k-nearest matrix neighbors. This model considers the associations among the time stamps and variables simultaneously. Fourth, we design two post-filling strategies to obtain a completed tri-state. The experimental results from the four-domain datasets show that (1) the tri-state has greater recall but lower precision; (2) the two post-filling strategies can slightly improve the recall; and (3) the along–across similarity model composed by the Triangle and Jaccard metrics are first recommended for new datasets.

show abstract

Large-scale User Visits Understanding and Forecasting with Deep Spatial-Temporal Tensor Factorization Framework

Cited by 12 publications

References 14 publications

Block Hankel Tensor ARIMA for Multiple Short Time Series Forecasting

Block Hankel Tensor ARIMA for Multiple Short Time Series Forecasting

Optimal Spend Rate Estimation and Pacing for Ad Campaigns with Budgets

Tri-Partition Alphabet-Based State Prediction for Multivariate Time-Series

Contact Info

Product

Resources

About