Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Dont Need All Eggs in One Basket: Reconstructing Composite Embeddings of Customers from Individual-Domain Embeddings

Dont Need All Eggs in One Basket: Reconstructing Composite Embeddings of Customers from... Although building a 360-degree comprehensive view of a customer has been a long-standing goal in marketing, this challenge has not been successfully addressed in many marketing applications because fractured customer data stored across different “silos” are hard to integrate under “one roof” for several reasons. Instead of integrating customer data, in this article we propose to integrate several domain-specific partial customer views into one consolidated or composite customer profile using a Deep Learning-based method that is theoretically grounded in Kolmogorov’s Mapping Neural Network Existence Theorem. Furthermore, our method needs to securely access domain-specific or siloed customer data only once for building the initial customer embeddings. We conduct extensive studies on two industrial applications to demonstrate that our method effectively reconstructs stable composite customer embeddings that constitute strong approximations of the ground-truth composite embeddings obtained from integrating the siloed raw customer data. Moreover, we show that these data-security preserving reconstructed composite embeddings not only perform as well as the original ground-truth embeddings but significantly outperform partial embeddings and state-of-the-art baselines in recommendation and consumer preference prediction tasks. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Management Information Systems (TMIS) Association for Computing Machinery

Dont Need All Eggs in One Basket: Reconstructing Composite Embeddings of Customers from Individual-Domain Embeddings

Download PDF
30 pages

Loading next page...
 
/lp/association-for-computing-machinery/dont-need-all-eggs-in-one-basket-reconstructing-composite-embeddings-rvS8GpoELC
Publisher
Association for Computing Machinery
Copyright
Copyright © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.
ISSN
2158-656X
eISSN
2158-6578
DOI
10.1145/3578710
Publisher site
See Article on Publisher Site

Abstract

Although building a 360-degree comprehensive view of a customer has been a long-standing goal in marketing, this challenge has not been successfully addressed in many marketing applications because fractured customer data stored across different “silos” are hard to integrate under “one roof” for several reasons. Instead of integrating customer data, in this article we propose to integrate several domain-specific partial customer views into one consolidated or composite customer profile using a Deep Learning-based method that is theoretically grounded in Kolmogorov’s Mapping Neural Network Existence Theorem. Furthermore, our method needs to securely access domain-specific or siloed customer data only once for building the initial customer embeddings. We conduct extensive studies on two industrial applications to demonstrate that our method effectively reconstructs stable composite customer embeddings that constitute strong approximations of the ground-truth composite embeddings obtained from integrating the siloed raw customer data. Moreover, we show that these data-security preserving reconstructed composite embeddings not only perform as well as the original ground-truth embeddings but significantly outperform partial embeddings and state-of-the-art baselines in recommendation and consumer preference prediction tasks.

Journal

ACM Transactions on Management Information Systems (TMIS) – Association for Computing Machinery

Published: Mar 13, 2023

Keywords: 360-degree view of customer

References

  • Deep learning with differential privacy
    Abadi, Martin; Chu, Andy; Goodfellow, Ian; McMahan, H. Brendan; Mironov, Ilya; Talwar, Kunal; Zhang, Li
  • Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions
    Adomavicius, Gediminas; Tuzhilin, Alexander
  • Recommender Systems, Vol
    Aggarwal, Charu C.
  • Big data analytics
    Ansari, Asim; Li, Yang
  • Probabilistic topic model for hybrid recommender systems: A stochastic variational Bayesian approach
    Ansari, Asim; Li, Yang; Zhang, Jonathan Z.
  • Customer channel migration
    Ansari, Asim; Mela, Carl F.; Neslin, Scott A.
  • A survey of deep learning methods for cyber security
    Berman, Daniel S.; Buczak, Anna L.; Chavis, Jeffrey S.; Corbett, Cherita L.
  • How Marketers Fulfill Customers’ Desire for Real-Time Brand Experiences
    Bhambhri, Anjul
  • What is a fair value of your recommendation list? In Proceedings of the 3rd Workshop on Experimental Economics and Machine Learning co-located with the 13th International Conference on Concept Lattices and Their Applications (CLA’16)
    Bobrikov, Vladimir; Nenova, Elena; Ignatov, Dmitry I.
  • Customer Relationship Management
    Buttle, Francis
  • Cross-domain recommender systems
    Cantador, Iván; Fernández-Tobías, Ignacio; Berkovsky, Shlomo; Cremonesi, Paolo
  • EXPRESS: Attribute sentiment scoring with online text reviews: Accounting for language structure and missing attributes
    Chakraborty, Ishita; Kim, Minkyung; Sudhir, K.
  • SMOTE: Synthetic minority over-sampling technique
    Chawla, Nitesh V.; Bowyer, Kevin W.; Hall, Lawrence O.; Kegelmeyer, W. Philip
  • Learning phrase representations using RNN encoder-decoder for statistical machine translation
    Cho, Kyunghyun; Van Merriënboer, Bart; Gulcehre, Caglar; Bahdanau, Dzmitry; Bougares, Fethi; Schwenk, Holger; Bengio, Yoshua
  • Empirical evaluation of gated recurrent neural networks on sequence modeling
    Chung, Junyoung; Gulcehre, Caglar; Cho, KyungHyun; Bengio, Yoshua
  • Approximation by supersitions of a single function
    Cybenko, G.
  • Recommendation system based on deep learning methods: A systematic review and new directions
    Da’u, Aminu; Salim, Naomie
  • Active learning with multiple localized regression models
    Deodhar, Meghana; Ghosh, Joydeep; Saar-Tsechansky, Maytal; Keshari, Vineet
  • Machine learning and marketing
    Dzyabura, Daria; Yoganarasimhan, Hema
  • Understanding branding in a digitally empowered world
    Erdem, Tülin; Keller, Kevin Lane; Kuksov, Dmitri; Pieters, Rik
  • On the approximate realization of continuous mappings by neural networks
    Funahashi, Ken-Ichi
  • A survey on deep learning for multimodal data fusion
    Gao, Jing; Li, Peng; Chen, Zhikui; Zhang, Jianing
  • The EU general data protection regulation (GDPR): European regulation that has a global impact
    Goddard, Michelle
  • Exploiting behavioral consistence for universal user representation
    Gu, Jie; Wang, Feng; Sun, Qinghui; Ye, Zhiquan; Xu, Xiaoxiao; Chen, Jingmin; Zhang, Jun
  • AWS re:Invent 2012, Day 1 Keynote
    Hastings, Reed
  • Neural collaborative filtering
    He, Xiangnan; Liao, Lizi; Zhang, Hanwang; Nie, Liqiang; Hu, Xia; Chua, Tat-Seng
  • Kolmogorov’s mapping neural network existence theorem
    Hecht-Nielsen, Robert
  • Session-based recommendations with recurrent neural networks
    Hidasi, Balázs; Karatzoglou, Alexandros; Baltrunas, Linas; Tikk, Domonkos
  • Reducing the dimensionality of data with neural networks
    Hinton, Geoffrey E.; Salakhutdinov, Ruslan R.
  • Long short-term memory
    Hochreiter, Sepp; Schmidhuber, Jürgen
  • Some new results on neural network approximation
    Hornik, Kurt
  • Multilayer feedforward networks are universal approximators
    Hornik, Kurt; Stinchcombe, Maxwell; White, Halbert
  • Towards universal sequence representation learning for recommender systems
    Hou, Yupeng; Mu, Shanlei; Zhao, Wayne Xin; Li, Yaliang; Ding, Bolin; Wen, Ji-Rong
  • Self-attentive sequential recommendation
    Kang, Wang-Cheng; McAuley, Julian
  • Deep learning for recommender systems
    Karatzoglou, Alexandros; Hidasi, Balázs
  • BERT: Pre-training of deep bidirectional transformers for language understanding
    Devlin, Jacob; Chang, Ming-Wei; Lee, Kenton; Toutanova, Kristina
  • Matrix factorization techniques for recommender systems
    Koren, Yehuda; Bell, Robert; Volinsky, Chris
  • Insight is power: Understanding the terms of the consumer-firm data exchange
    Krafft, Manfred; Kumar, V.; Harmeling, Colleen; Singh, Siddharth; Zhu, Ting; Chen, Jialie; Duncan, Tom; Fortin, Whitney; Rosa, Erin
  • Understanding customer experience throughout the customer journey
    Lemon, Katherine N.; Verhoef, Peter C.
  • RecGURU: Adversarial learning of generalized user representations for cross-domain recommendation
    Li, Chenglin; Zhao, Mingjun; Zhang, Huanming; Yu, Chenyun; Cheng, Lei; Shu, Guoqiang; Kong, Beibei; Niu, Di
  • PURS: Personalized unexpected recommender system for improving user satisfaction
    Li, Pan; Que, Maofei; Jiang, Zhichao; Hu, Yao; Tuzhilin, Alexander
  • DDTCDR: Deep dual transfer cross domain recommendation
    Li, Pan; Tuzhilin, Alexander
  • Privacy and security issues in deep learning: A survey
    Liu, Ximeng; Xie, Lehui; Wang, Yaopeng; Zou, Jian; Xiong, Jinbo; Ying, Zuobin; Vasilakos, Athanasios V.
  • Master Data Management
    Loshin, David
  • Using Information to Develop a Culture of Customer Centricity: Customer Centricity, Analytics, and Information Utilization
    Loshin, David; Reifer, Abie
  • Machine learning and AI in marketing–Connecting computing power to human insights
    Ma, Liye; Sun, Baohong
  • Perils of location tracking? Personalized and interpretable privacy preservation in consumer mobile trajectories
    Macha, Meghanath; Li, Beibei; Foutz, Natasha Zhang; Ghose, Anindya
  • Scalable deep learning on distributed infrastructures: Challenges, techniques, and tools
    Mayer, Ruben; Jacobsen, Hans-Arno
  • The Age of Analytics: Competing in a Data-driven World
    McKinsey,
  • Inductive expert system design: Maximizing system value
    Mookerjee, Vijay S.; Santos, Brian L. Dos
  • Redesigning case retrieval to reduce information acquisition costs
    Mookerjee, Vijay S.; Mannino, Michael V.
  • Information acquisition policies for resource allocation among multiple agents
    Moore, James C.; Rao, H. Raghav; Whinston, A.; Nam, Kichan; Raghu, T. S.
  • A model of decision-making with sequential information-acquisition (part 1)
    Moore, James C.; Whinston, Andrew B.
  • A model of decision-making with sequential information-acquisition (part 2)
    Moore, James C.; Whinston, Andrew B.
  • The role of the management sciences in research on personalization
    Murthi, B. P. S.; Sarkar, Sumit
  • Deep learning applications and challenges in big data analytics
    Najafabadi, Maryam M.; Villanustre, Flavio; Khoshgoftaar, Taghi M.; Seliya, Naeem; Wald, Randall; Muharemagic, Edin
  • Frontiers: How effective is third-party consumer profiling? Evidence from field studies
    Neumann, Nico; Tucker, Catherine E.; Whitfield, Timothy
  • Perceive your users in depth: Learning universal user representations from multiple e-commerce tasks
    Ni, Yabo; Ou, Dan; Liu, Shichen; Li, Xiang; Ou, Wenwu; Zeng, Anxiang; Si, Luo
  • Personalization from incomplete data: What you don’t know can hurt
    Padmanabhan, Balaji; Zheng, Zhiqiang; Kimbrough, Steven O.
  • An empirical analysis of the value of complete information for eCRM models
    Padmanabhan, Balaji; Zheng, Zhiqiang; Kimbrough, Steven O.
  • Sequence-aware recommender systems
    Quadrana, Massimo; Cremonesi, Paolo; Jannach, Dietmar
  • Recommender systems: Introduction and challenges
    Ricci, Francesco; Rokach, Lior; Shapira, Bracha
  • Learning Internal Representations by Error Propagation
    Rumelhart, David E.; Hinton, Geoffrey E.; Williams, Ronald J.
  • Recommender systems for large-scale e-commerce: Scalable neighborhood formation using clustering
    Sarwar, Badrul M.; Karypis, George; Konstan, Joseph; Riedl, John
  • The path to customer centricity
    Shah, Denish; Rust, Roland T.; Parasuraman, Ananthanarayanan; Staelin, Richard; Day, George S.
  • Evaluating recommendation systems
    Shani, Guy; Gunawardana, Asela
  • mvn2vec: Preservation and collaboration in multi-view network embedding
    Shi, Yu; Han, Fangqiu; He, Xinwei; He, Xinran; Yang, Carl; Luo, Jie; Han, Jiawei
  • Customer relationship management mechanisms: A systematic review of the state of the art literature and recommendations for future research
    Soltani, Zeynab; Navimipour, Nima Jafari
  • BERT4Rec: Sequential recommendation with bidirectional encoder representations from transformer
    Sun, Fei; Liu, Jun; Wu, Jian; Pei, Changhua; Lin, Xiao; Ou, Wenwu; Jiang, Peng
  • Introduction to Data Mining
    Tan, Pang-Ning; Steinbach, Michael; Kumar, Vipin
  • Crumbs of the cookie: User profiling in customer-base analysis and behavioral targeting
    Trusov, Michael; Ma, Liye; Jamal, Zainab
  • Personalization: The state of the art and future directions
    Tuzhilin, Alexander
  • Customer relationship management and Web mining: The next frontier
    Tuzhilin, Alexander
  • Information governance program implementation and strategies in banking sector
    Tyagi, Ayan
  • Context-aware recommendations based on deep learning frameworks
    Unger, Moshe; Tuzhilin, Alexander; Livne, Amit
  • Collaborative deep learning for recommender systems
    Wang, Hao; Wang, Naiyan; Yeung, Dit-Yan
  • Sequential recommender systems: Challenges, progress and prospects
    Wang, S.; Hu, L.; Wang, Y.; Cao, L.; Sheng, Q. Z.; Orgun, M.
  • Marketing analytics for data-rich environments
    Wedel, Michel; Kannan, P. K.
  • Deep learning via semi-supervised embedding
    Weston, Jason; Ratle, Frédéric; Mobahi, Hossein; Collobert, Ronan
  • Battle of the channels: The impact of tablets on digital commerce
    Xu, Kaiquan; Chan, Jason; Ghose, Anindya; Han, Sang Pil
  • Federated recommendation systems
    Yang, Liu; Tan, Ben; Zheng, Vincent W.; Chen, Kai; Yang, Qiang
  • Adaptive user modeling with long and short-term preferences for personalized recommendation
    Yu, Zeping; Lian, Jianxun; Mahmoody, Ahmad; Liu, Gongshen; Xie, Xing
  • A survey on federated learning
    Zhang, Chen; Xie, Yu; Bai, Hang; Yu, Bin; Li, Weihong; Gao, Yuan
  • A recommendation model based on deep neural network
    Zhang, Libo; Luo, Tiejian; Zhang, Fei; Wu, Yanjun
  • Frontiers: Can an artificial intelligence algorithm mitigate racial economic inequality? An analysis in the context of airbnb
    Zhang, Shunyuan; Mehta, Nitin; Singh, Param Vir; Srinivasan, Kannan
  • Deep learning based recommender system: A survey and new perspectives
    Zhang, Shuai; Yao, Lina; Sun, Aixin; Tay, Yi
  • Selectively acquiring customer information: A new data acquisition problem and an active learning-based solution
    Zheng, Zhiqiang; Padmanabhan, Balaji
  • Selectively acquiring customer information: A new data acquisition problem and an active learning-based solution
    Zheng, Zhiqiang; Padmanabhan, Balaji