Deep Sequence Learning with Auxiliary Information for Traffic Prediction

Liao, Binbing; Zhang, Jingqing; Wu, Chao; McIlwraith, Douglas; Chen, Tong; Yang, Shengwen; Guo, Yike; Wu, Fei

doi:10.1145/3219819.3219895

Cited by 181 publications

(87 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…10. In order to reduce the dimensionality of the contextual data yet extract meaningful information we use a standard sparse autoencoder (SAE) [34], [35,Ch.14]. In brief, a SAE consists of two feedforward neural networks: an encoder (with an output layer of size 1 in our case) and a decoder (with an output layer of size equal to the dimensions of the input of the encoder).…”

Section: B Resource Utilizationmentioning

confidence: 99%

ARENA: A Data-Driven Radio Access Networks Analysis of Football Events

Zanzi

Sciancalepore²,

García‐Saavedra³

et al. 2020

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

Mass events represent one of the most challenging scenarios for mobile networks because, although their date and time are usually known in advance, the actual demand for resources is difficult to predict due to its dependency on many different factors. Based on data provided by a major European carrier during mass events in a football stadium comprising up to 30.000 people, 16 base station sectors and 1 Km 2 area, we performed a data-driven analysis of the radio access network infrastructure dynamics during such events. Given the insights obtained from the analysis, we developed ARENA, a model-free deep learning Radio Access Network (RAN) capacity forecasting solution that, taking as input past network monitoring data and events context information, provides guidance to mobile operators on the expected RAN capacity needed during a future event. Our results, validated against real events contained in the dataset, illustrate the effectiveness of our proposed solution.

show abstract

Section: B Resource Utilizationmentioning

confidence: 99%

ARENA: A Data-Driven Radio Access Networks Analysis of Football Events

Zanzi

Sciancalepore²,

García‐Saavedra³

et al. 2020

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

show abstract

“…The fundamental building block of marketing budget allocation is to forecast sales response of each segment if the budget is spend on it. As black-box forecasting methods, neural networks are very powerful and have wide applications [21,33,35]. However, there are many challenges to translate black-box forecasting into allocation decisions [2].…”

Section: Logit Response Modelmentioning

confidence: 99%

“…In order to resolve how to allocate the budget into each market-segment, we need to forecast sales response of each segment if the budget is spent on it. Although black-box forecasting methods, such as neural networks, have been widely used in many applications [21,33,35], there are several gaps between forecasting and decision making [2]. One of the biggest challenges is that it is too difficult to translate black-box forecasting into allocation decisions.…”

Section: Introductionmentioning

confidence: 99%

A Unified Framework for Marketing Budget Allocation

Zhao

Hua

Yan

et al. 2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

While marketing budget allocation has been studied for decades in traditional business, nowadays online business brings much more challenges due to the dynamic environment and complex decision-making process. In this paper, we present a novel unified framework for marketing budget allocation. By leveraging abundant data, the proposed data-driven approach can help us to overcome the challenges and make more informed decisions. In our approach, a semi-black-box model is built to forecast the dynamic market response and an efficient optimization method is proposed to solve the complex allocation task. First, the response in each market-segment is forecasted by exploring historical data through a semi-black-box model, where the capability of logit demand curve is enhanced by neural networks. The response model reveals relationship between sales and marketing cost. Based on the learned model, budget allocation is then formulated as an optimization problem, and we design efficient algorithms to solve it in both continuous and discrete settings. Several kinds of business constraints are supported in one unified optimization paradigm, including cost upper bound, profit lower bound, or ROI lower bound. The proposed framework is easy to implement and readily to handle large-scale problems. It has been successfully applied to many scenarios in Alibaba Group. The results of both offline experiments and online A/B testing demonstrate its effectiveness.

show abstract

“…Furthermore, the sequence to sequence model (Seq2Seq) was proposed by Cho et al [12] in 2014 to solve the problem of the machine translation system. And then, it was used to predict traffic speed sequences successfully [16], [17] in 2018. The attention mechanism proposed by Dzmitry Bahdanau et al [18] to improve Seq2Seqs in 2015.…”

Section: Introductionmentioning

confidence: 99%

“…The traffic speed dataset was collected from Liao et al [16]. The traffic speed data of each road segment recorded at an interval of 15 minutes per day.…”

Section: Introductionmentioning

confidence: 99%

Triplet Decoders Neural Network Ensemble System and T-Conversion for Traffic Speed Sequence Prediction

2019

View full text Add to dashboard Cite

Traffic flow prediction is essential in Intelligent Transportation System (ITS). Due to the complexity of the traffic environment, predicting future traffic speed is difficult. A lot of methods have been proposed to forecast traffic flow, such as support vector regression (SVR), recurrent neural networks (RNN), and so on. However, there are few ensemble models methods for predicting traffic flow, especially for predicting multi-step traffic speed. Meanwhile, these ensemble methods often use many base models for regression. Thus, the performances of these existing methods are worth exploring for multi-step traffic forecasts with few base models. Besides, this paper proposes a model based on ensemble models, called ''Triplet Decoders Neural Network'' (TDNN), to compare with these methods. By analyzing the characteristic of traffic speed data, this paper also proposes a data preprocessing model called ''T-Conversion'' to help RNN capturing long-term dependencies. Our experiments are implemented based on real traffic speed data from Baidu in Beijing, China because the prediction for complex traffic is more valuable. With these new novel ideas, our experiments show the superior performances of TDNN, and the significant effect of T-Conversion for predicting traffic speed sequences. INDEX TERMS Recurrent neural network (RNN), long short term memory (LSTM), gated recurrent unit (GRU), sequence to sequence (Seq2Seq), ensemble models.

show abstract

Deep Sequence Learning with Auxiliary Information for Traffic Prediction

Cited by 181 publications

References 31 publications

ARENA: A Data-Driven Radio Access Networks Analysis of Football Events

ARENA: A Data-Driven Radio Access Networks Analysis of Football Events

A Unified Framework for Marketing Budget Allocation

Triplet Decoders Neural Network Ensemble System and T-Conversion for Traffic Speed Sequence Prediction

Contact Info

Product

Resources

About