A Novel Framework for Online Sales Burst Prediction

With the rapid growth of e-commerce, a large number of online transactions are processed every day. In this paper, we take the initiative to conduct a systematic study of the challenging prediction problems of sales bursts. Here, we propose a novel model to detect bursts, find the bursty features, namely the start time of the burst, the peak value of the burst and the off-burst value, and predict the entire burst shape. Our model analyzes the features of similar sales bursts in the same category, and applies them to generate the prediction. We argue that the framework is capable of capturing the seasonal and categorical features of sales burst. Based on the real data from JD.com, we conduct extensive experiments and discover that the proposed model makes a relative MSE improvement of 71% and 30% over LSTM and ARMA.

[1]  Eamonn J. Keogh,et al.  Making Time-Series Classification More Accurate Using Learned Constraints , 2004, SDM.

[2]  Zhe Zhao,et al.  Real-Time Predicting Bursting Hashtags on Twitter , 2014, WAIM.

[3]  Oliver Vornberger,et al.  Sales forecasting using neural networks , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[4]  Delbert Dueck,et al.  Clustering by Passing Messages Between Data Points , 2007, Science.

[5]  Ramanathan V. Guha,et al.  The predictive power of online chatter , 2005, KDD '05.

[6]  Sachin Tripathi,et al.  E-Commerce: True Indian Picture , 2012 .

[7]  Zhe Zhao,et al.  Predicting bursts and popularity of hashtags in real-time , 2014, SIGIR.

[8]  David Lazer,et al.  #Bigbirds Never Die: Understanding Social Dynamics of Emergent Hashtags , 2013, ICWSM.

[9]  Andreas S. Weigend,et al.  Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[10]  Gao Cong,et al.  On predicting the popularity of newly emerging hashtags in Twitter , 2013, J. Assoc. Inf. Sci. Technol..

[11]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[12]  Zhe Zhao,et al.  On the Real-time Prediction Problems of Bursting Hashtags in Twitter , 2014, ArXiv.

[13]  Ilia Petrov,et al.  Sales Prediction with Parametrized Time Series Analysis , 2013 .

[14]  Albert-Laszló Barabási,et al.  Bursts : the hidden patterns behind everything we do, from your e-mail to bloody crusades , 2011 .