Filters








27,987 Hits in 4.6 sec

Customer Purchase Intent Prediction under Online Multi-Channel Promotion: A Feature-Combined Deep Learning Framework

Ling Chen, Zhang Tao, Chen Yuan
2019 IEEE Access  
We apply our method in a real prediction task for online multichannel promotion for concert tickets.  ...  The micro-level customer purchase intent in promotions is crucial for the overall purchase conversion rate of promotions.  ...  Given the popularity of online promotions through multiple distribution channels (''multi-channel promotion''), it is necessary for marketers to pay attention to customers' online browsing behavior between  ... 
doi:10.1109/access.2019.2935121 fatcat:wps7kk47jvfxbovm64dkidg5au

TPG-DNN: A Method for User Intent Prediction Based on Total Probability Formula and GRU Loss with Multi-task Learning [article]

Jingxing Jiang, Zhubin Wang, Fei Fang, Binqiang Zhao
2020 arXiv   pre-print
In this paper, we propose a novel user intent prediction model, TPG-DNN, to complete the challenging task, which is based on adaptive gated recurrent unit (GRU) loss function with multi-task learning.  ...  Critical as is to improve the online shopping experience for customers and merchants, how to find a proper approach for user intent prediction are paid great attention in both industry and academia.  ...  Based on the multi-task learning framework, they also build a time series model for multiple user behaviors.  ... 
arXiv:2008.02122v1 fatcat:d6x7gywndveb7eh3ddhn2mtx5e

Scenario Adaptive Mixture-of-Experts for Promotion-Aware Click-Through Rate Prediction [article]

Xiaofeng Pan, Yibin Shen, Jing Zhang, Keren Yu, Hong Wen, Shui Liu, Chengjun Mao, Bo Cao
2022 arXiv   pre-print
Promotions are becoming more important and prevalent in e-commerce platforms to attract customers and boost sales.  ...  To the best of our knowledge, this is the first study for promotion-aware CTR prediction. Experimental results on real-world datasets validate the superiority of SAME.  ...  methods; and 3) multi-task learning based methods.  ... 
arXiv:2112.13747v2 fatcat:qu7qtomqfbc47j4wrwbb2d7quq

Dialog Router: Automated Dialog Transition via Multi-Task Learning

Ziming Huang, Zhuoxuan Jiang, Hao Chen, Xue Han, Yabin Dang
2021 AAAI Conference on Artificial Intelligence  
In addition, for learning the multi-task model, the training data and labels are easy to collect from human-to-human historical dialog logs, and the Dialog Router can be easily integrated into the majority  ...  It is equipped with a multi-task learning model to automatically capture the underlying correlation between multiple related tasks, i.e. dialog classification and regression, and greatly reduce human labor  ...  We thank all the reviewers for their insightful comments.  ... 
dblp:conf/aaai/HuangJCHD21 fatcat:ca4c3fvw7fc4vezgyapbdihtbm

Markdowns in E-Commerce Fresh Retail: A Counterfactual Prediction and Multi-Period Optimization Approach [article]

Junhao Hua, Ling Yan, Huan Xu, Cheng Yang
2021 arXiv   pre-print
In this paper, by leveraging abundant observational transaction data, we propose a novel data-driven and interpretable pricing approach for markdowns, consisting of counterfactual prediction and multi-period  ...  Based on the stochastic model, we derive a sequential pricing strategy by Markov decision process, and design a two-stage algorithm to solve it. The proposed algorithm is very efficient.  ...  We emphasize that the sales forecasting module only predicts the sales at an average of historical discounts , i.e., We call ( , ) as base discount and base sales pair of product .  ... 
arXiv:2105.08313v2 fatcat:atxzob6c7veb5a6725o7h3lt54

Prediction of Online Consumers' Repeat Purchase Behavior via BERT-MLP Model

Junchao Dong, Tinghui Huang, Liang Min, Wenyan Wang
2022 Journal of Electronic Research and Application  
It is an effective means for merchants to carry out precision marketing and improve ROI by using historical user behavior data obtained from promotional activities in order to build a model to predict  ...  the repeat purchase behavior of users after promotional activities.  ...  In order to attract more consumers, e-commerce platforms have been inviting well-known figures and online celebrities to play a part in live sales promotions on special days, such as "Double 11" and "618  ... 
doi:10.26689/jera.v6i3.4010 fatcat:dxilkygsivarbff7espxnhu234

Decision tree models for profiling ski resorts' promotional and advertising strategies and the impact on sales

Peter Duchessi, Eitel J.M. Lauría
2013 Expert systems with applications  
Based on survey data, this paper builds decision tree models to profile the online and mobile technologies and services that ski resorts use for their promotional and advertising strategies for two important  ...  The research is the first of its type in the ski industry and represents a novel use of decision tree models for profiling promotional and advertising strategies.  ...  For example, ski resorts can use resort websites, Groupon (i.e., an online coupon service), and Foursquare (i.e., a location-based service) for promoting and advertising to online followers and prospective  ... 
doi:10.1016/j.eswa.2013.05.017 fatcat:t3rx2erov5hntd3un5ijif2pou

Who is next: rising star prediction via diffusion of user interest in social networks [article]

Xuan Yang, Yang Yang, Jintao Su, Yifei Sun, Shen Fan, Zhongyao Wang, Jun Zhang, Jingmin Chen
2022 arXiv   pre-print
Finding items with potential to increase sales is of great importance in online market. In this paper, we propose to study this novel and practical problem: rising star prediction.  ...  items, which cannot be solved by existing sales prediction methods.  ...  In online markets, many promotion campaigns are conducted to stimulate sales [6] .  ... 
arXiv:2203.14807v2 fatcat:ah4i5bdct5hxfdzqvjazh5ce2u

Sequential Recommendation in Online Games with Multiple Sequences, Tasks and User Levels [article]

Si Chen, Yuqiu Qian, Hui Li, Chen Lin
2021 arXiv   pre-print
Recommender systems (RS) for online games face unique challenges since they must fulfill players' distinct desires, at different user levels, based on their action sequences of various action types.  ...  Online gaming is a multi-billion-dollar industry, which is growing faster than ever before.  ...  RS not only assists users in searching for desirable targets but also helps e-commerce platforms promote their products and boost sales [1] .  ... 
arXiv:2102.06950v1 fatcat:b6eisor2s5gkjh3wlfm46wwjje

Methods of Analyzing Consumer Behavior Based on Multi-Source Data

Pawel Rymarczyk, Piotr Bednarczuk, Ryszard Nowak, Tomasz Cieplak
2021 EUROPEAN RESEARCH STUDIES JOURNAL  
Originality/Value: A novelty is the construction of a multi-source model for data analysis, where appropriate predictive models were built to predict the level of sales with the use of machine learning  ...  Abstarct: Purpose: The aim of the article is to develop a system for analyzing processes and data from various data sources based on machine learning methods.  ...  The goal is to build a predictive model that allows you to predict the level of sales.  ... 
doi:10.35808/ersj/2229 fatcat:vzo67iso6nf2flpwdaaayxfhaq

Sentiment and topic analysis on social media

Shu Huang, Wei Peng, Jingxuan Li, Dongwon Lee
2013 Proceedings of the 5th Annual ACM Web Science Conference on - WebSci '13  
As such, in recent years, many solutions have been proposed for both tasks.  ...  It incorporates results of each task from prior steps to promote and reinforce the other iteratively.  ...  To address the problem of multi-label multi-task classification, we propose an algorithm based on multi-label learning and utilize association between tasks to promote classification accuracy.  ... 
doi:10.1145/2464464.2464512 dblp:conf/websci/HuangPLL13 fatcat:3f3ps5czu5bhbhdgtquha7dzgu

The Analysis of Intelligent Marketing Platform in High-tech Products by Data Mining Algorithm

Chung-Chih Lee, Hsing-Chau Tseng, Chun-Chu Liu, Huei-Jeng Chou
2022 Wseas Transactions on Business and Economics  
Modern data mining analysis mode has become the main solution for data problems.  ...  The novel social network based on internet technology occupies an important part of the marketing, and has also been widely concerned by the academic community, because the internet makes information data  ...  After obtaining the characteristics from each type of data, the regression method based on multi-task learning can predict the time value.  ... 
doi:10.37394/23207.2022.19.50 fatcat:aoqf4ko5hrca3awizji5jy6ixm

PromotionLens: Inspecting Promotion Strategies of Online E-commerce via Visual Analytics [article]

Chenyang Zhang, Xiyuan Wang, Chuyi Zhao, Yijing Ren, Tianyu Zhang, Zhenhui Peng, Xiaomeng Fan, Quan Li
2022 arXiv   pre-print
Current approaches to designing promotion strategies are either based on econometrics, which may not scale to large amounts of sales data, or are spontaneous and provide little explanation of sales volume  ...  Promotions are commonly used by e-commerce merchants to boost sales.  ...  ACKNOWLEDGMENTS We are grateful for the valuable feedback and comments provided by the anonymous reviewers.  ... 
arXiv:2208.01404v1 fatcat:pio46hvt2jdobhjgrxht5faipi

EdgeDIPN: a Unified Deep Intent Prediction Network Deployed at the Edge

Long Guo, Lifeng Hua, Rongfei Jia, Fei Fang, Binqiang Zhao, Bin Cui
2020 Proceedings of the VLDB Endowment  
To improve online shopping experience for consumers and increase sales for sellers, it is important to understand user intent accurately and be notified of its change timely.  ...  We propose to train EdgeDIPN with multi-task learning, by which EdgeDIPN can share representations between different tasks for better performance and saving edge resources in the meantime.  ...  In this section, we introduce a novel push notification strategy for the soon-to-expire coupons based on the real-time purchasing intent predicted by EdgeDIPN in online traffic of Taobao.  ... 
doi:10.5555/3430915.3442431 dblp:journals/pvldb/GuoHJFZ020 fatcat:ktmk6plccbguxk54ojoyji777i

A prediction model for benefitting e-commerce through usage of regional data: A new framework

Shefali Singhal, Poonam Tanwar
2021 IAES International Journal of Artificial Intelligence (IJ-AI)  
Datasets and their combinations based on multiple attributes are input for the proposed predictive system.  ...  For this research work the data has been collected on the basis of area-wise, like, country-based seggregation.  ...  [5] examined the online reviews to predict product sales. Agarwal [6] found few Indian brands which promote the handicraft sale.  ... 
doi:10.11591/ijai.v10.i4.pp1009-1018 fatcat:aextcnyyyfg3he5dwolcigjfdu
« Previous Showing results 1 — 15 out of 27,987 results