Beyond Complements and Substitutes: A Graph Neural Network Approach for Collaborative Retail Sales Forecasting

References

• Abbasi A, Parsons J, Pant G, Sheng ORL, Sarker S (2024) Pathways for design research on artificial intelligence. Inform. Systems Res. 35(2):441–459.Link, Google Scholar
• Avery J, Steenburgh TJ, Deighton JA, Caravella M (2009) Adding bricks to clicks. The Contingencies Driving Cannibalization and Complementarity in Multichannel Retailing (Harvard Business School, Cambridge, MA).Google Scholar
• Aviv Y (2007) On the benefits of collaborative forecasting partnerships between retailers and manufacturers. Management Sci. 53(5):777–794.Link, Google Scholar
• Bai L, Yao L, Wang X, Li C, Zhang X (2021) Deep spatial-temporal sequence modeling for multi-step passenger demand prediction. Future Gener. Comput. Systems. (121):25–34.Crossref, Google Scholar
• Balcilar M, Renton G, Héroux P, Gaüzère B, Adam S, Honeine P (2021) Analyzing the expressive power of graph neural networks in a spectral perspective. Proc. 9th Internat. Conf. Learn. Representations (OpenReview.net), 1–26.Google Scholar
• Bandyopadhyay S (2009) A dynamic model of cross-category competition: Theory, tests and applications. J. Retail. 85(4):468–479.Crossref, Google Scholar
• Bi X, Adomavicius G, Li W, Qu A (2022) Improving sales forecasting accuracy: A tensor factorization approach with demand awareness. Informs J. Comput. 34(3):1644–1660.Link, Google Scholar
• Bo D, Wang X, Shi C, Japa SH (2021) Beyond low-frequency information in graph convolutional networks. Proc. 35th AAAI Conf. Artificial Intelligence (AAAI Press, Palo Alto, CA), 3950–3957.Google Scholar
• Borah A, Tellis GJ (2016) Halo (spillover) effects in social media: Do product recalls of one brand hurt or help rival brands? J. Marketing Res. 53(2):143–160.Crossref, Google Scholar
• Cai W, Liang Y, Liu X, Feng J, Wu Y (2024) Msgnet: Learning multi-scale inter-series correlations for multivariate time series forecasting. Proc. 38th AAAI Conf. Artificial Intelligence (AAAI Press, Palo Alto, CA), 11141–11149.Google Scholar
• Chen ZY, Fan ZP, Sun M (2023c) Machine learning methods for data-driven demand estimation and assortment planning considering cross-selling and substitutions. Informs J. Comput. 35(1):158–177.Link, Google Scholar
• Chen Y, Wei Z, and, Huang X (2018) Incorporating corporation relationship via graph convolutional neural networks for stock price prediction. Proc. 27th ACM Internat. Conf. Inform. Knowledge Management (Association for Computing Machinery, New York), 1655–1658.Google Scholar
• Chen G, Huang L, Xiao S, Zhang C, Zhao H (2024) Attending to customer attention: A novel deep learning method for leveraging multimodal online reviews to enhance sales prediction. Inform. Systems Res. 35(2):829–849.Link, Google Scholar
• Chen L, Chen D, Shang Z, Wu B, Zheng C, Wen B, Zhang W (2023b) Multi-scale adaptive graph neural network for multivariate time series forecasting. IEEE Trans. Knowledge Data Engrg. 35(10):10748–10761.Crossref, Google Scholar
• Chen H, He J, Xu W, Feng T, Liu M, Song T, Yao R, Qiao Y (2023a) Enhanced multi-relationships integration graph convolutional network for inferring substitutable and complementary items. Proc. 37th AAAI Conf. Artificial Intelligence (AAAI Press, Palo Alto, CA), 4157–4165.Google Scholar
• Cho K, Van Merriënboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using Rnn encoder-decoder for statistical machine translation. Proc. Conf. Empirical Methods Natl. Language Processing (Association for Computational Linguistics, Stroudsburg, PA), 1724–1734.Google Scholar
• Cui R, Gallino S, Moreno A, Zhang DJ (2018) The operational value of social media information. Prod. Oper. Management 27(10):1749–1769.Crossref, Google Scholar
• Deng S, Wang S, Rangwala H, Wang L, and, Ning Y (2020) Cola-Gnn: Cross-location attention based graph neural networks for long-term ili prediction. Proc. 29th ACM Internat. Conf. Inform. Knowledge Management (Association for Computing Machinery, New York), 245–254.Google Scholar
• Derr T, Ma Y, Tang J (2018) Signed graph convolutional networks. Proc. IEEE Internat. Conf. Data Mining (IEEE, Piscataway, NJ), 929–934.Google Scholar
• Dhar V, Geva T, Oestreicher-Singer G, Sundararajan A (2014) Prediction in economic networks. Inform. Systems Res. 25(2):264–284.Link, Google Scholar
• Diebold FX, Mariano RS (2002) Comparing predictive accuracy. J. Bus. Econom. Statist. 20(1):134–144.Crossref, Google Scholar
• Dong Y, Huang X, Sinha KK, Xu K (2014) Collaborative demand forecasting: Toward the design of an exception-based forecasting mechanism. J. Management Inform. Systems 31(2):245–284.Crossref, Google Scholar
• Ergin E, Gümüş M, Yang N (2022) An empirical analysis of intra-firm product substitutability in fashion retailing. Production Oper. Management 31(2):607–621.Crossref, Google Scholar
• Feng F, He X, Wang X, Luo C, Liu Y, Chua T-S (2019) Temporal relational ranking for stock rrediction. ACM Trans. Inform. Systems 37(2):1–30.Crossref, Google Scholar
• Fildes R, Kolassa S, Ma S (2022a) Post-script—Retail forecasting: Research and practice. Internat. J. Forecasting 38(4):1319–1324.Crossref, Google Scholar
• Fildes R, Ma S, Kolassa S (2022b) Retail forecasting: Research and practice. Internat. J. Forecasting 38(4):1283–1318.Crossref, Google Scholar
• Gelper S, Wilms I, Croux C (2016) Identifying demand effects in a large network of product categories. J. Retail. 92(1):25–39.Crossref, Google Scholar
• Glaeser CK, Fisher M, Su X (2019) Optimal retail location: Empirical methodology and application to practice. Manufacturing Service Oper. Management 21(1):86–102.Link, Google Scholar
• Gregor S, Hevner AR (2013) Positioning and presenting design science research for maximum impact. MIS Quart. 37(2):337–355.Crossref, Google Scholar
• Hadsell R, Chopra S, LeCun Y (2006) Dimensionality reduction by learning an invariant mapping. Proc. IEEE Comput. Soc. Conf. Comput. Vision Pattern Recognition (IEEE, Piscataway, NJ), 1735–1742.Google Scholar
• Hao J, Zhao T, Li J, Dong XL, Faloutsos C, Sun Y, Wang W (2020) P-companion: A principled framework for diversified complementary product recommendation. Proc. 29th ACM Internat. Conf. Inform. Knowledge Management (Association for Computing Machinery, New York), 2517–2524.Google Scholar
• Hsu YL, Tsai YC, Li CT (2021) Fingat: Financial graph attention networks for recommending top-K profitable stocks. IEEE Trans. Knowledge Data Engrg. 35(1):469–481.Google Scholar
• Huang T, Bergman D, Gopal R (2019) Predictive and prescriptive analytics for location selection of add-on retail products. Production Oper. Management 28(7):1858–1877.Crossref, Google Scholar
• Huang T, Fildes R, Soopramanien D (2014) The value of competitive information in forecasting fmcg retail product sales and the variable selection problem. Eur. J. Oper. Res. 237(2):738–748.Crossref, Google Scholar
• Huber J, Stuckenschmidt H (2020) Daily retail demand forecasting using machine learning with emphasis on calendric special days. Internat. J. Forecasting 36(4):1420–1438.Crossref, Google Scholar
• Jabr W, Zheng Z (2014) Know yourself and know your enemy. MIS Quart. 38(3):635–654.Crossref, Google Scholar
• Jiang Z, Li J, Zhang D (2024) A high-dimensional choice model for online retailing. Management Sci. Preprint, submitted July 19, https://doi.org/10.1287/mnsc.2020.02715.Link, Google Scholar
• Ke C, Wang R (2022) Cross-category retailing management: Substitution and complementarity. Manufacturing Service Oper. Management 24(2):1128–1145.Link, Google Scholar
• Kitchens B, Dobolyi D, Li J, Abbasi A (2018) Advanced customer analytics: Strategic value through integration of relationship-oriented big data. J. Management Inform. Systems 35(2):540–574.Crossref, Google Scholar
• Kotler P, Armstrong G (2010) Principles of Marketing (Pearson Education, Hoboken, NJ).Google Scholar
• Kwark Y, Lee GM, Pavlou PA, Qiu L (2021) On the spillover effects of online product reviews on purchases: Evidence from clickstream data. Inform. Systems Res. 32(3):895–913.Link, Google Scholar
• Lee K, Ram S (2024) Explainable deep learning for false information identification: An argumentation theory approach. Inform. Systems Res. 35(2):890–907.Link, Google Scholar
• Lee S, Kim J, Allenby GM (2013) A direct utility model for asymmetric complements. Marketing Sci. 32(3):454–470.Link, Google Scholar
• Lei D, Qi Y, Liu S, Geng D, Zhang J, Hu H, Shen Z-JM (2024) Pooling and boosting for demand prediction in retail: A transfer learning approach. Manufacturing Service Oper. Management, ePub ahead of print May 30, https://doi.org/10.1287/msom.2022.0453.Link, Google Scholar
• Li Y, Yu R, Shahabi C, Liu Y (2018) Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. Proc. 6th Internat. Conf. Learn. Representations (OpenReview.net).Google Scholar
• Lim B, Arık SÖ, Loeff N, Pfister T (2021) Temporal fusion transformers for interpretable multi-horizon time series forecasting. Internat. J. Forecasting 37(4):1748–1764.Crossref, Google Scholar
• Lin S, Luo M, Walker RJ, Liu X, Hwang SA, Chinery R (2009) Extreme high temperatures and hospital admissions for respiratory and cardiovascular diseases. Epidemiology 20(5):738–746.Crossref, Google Scholar
• Liu W, Zhang Y, Wang J, He Y, Caverlee J, Chan PP, Yeung DS, Heng P-A (2021) Item relationship graph neural networks for E-Commerce. IEEE Trans. Neural Networks Learn. Systems 33(9):4785–4799.Crossref, Google Scholar
• Liu X, Lee D, Srinivasan K (2019) Large-scale cross-category analysis of consumer review content on sales conversion leveraging deep learning. J. Marketing Res. 56(6):918–943.Crossref, Google Scholar
• Liu Y, Gu Y, Ding Z, Gao J, Guo Z, Bao Y, Yan W (2020a) Decoupled graph convolution network for inferring substitutable and complementary items. Proc. 29th ACM Internat. Conf. Inform. Knowledge Management (Association for Computing Machinery, New York), 2621–2628.Google Scholar
• Liu Y, Pant G, Sheng OR (2020b) Predicting labor market competition: Leveraging interfirm network and employee skills. Inform. Systems Res. 31(4):1443–1466.Link, Google Scholar
• Liu Y, Qian Y, Jiang Y, Shang J (2020c) Using favorite data to analyze asymmetric competition: Machine learning models. Eur. J. Oper. Res. 287(2):600–615.Crossref, Google Scholar
• Lv M, Hong Z, Chen L, Chen T, Zhu T, Ji S (2020) Temporal multi-graph convolutional network for traffic flow prediction. IEEE Trans. Intelligent Transport. Systems 22(6):3337–3348.Crossref, Google Scholar
• Ma S (2024) Retail store-Sku level replenishment planning with attribute-space graph recurrent neural networks. Expert Syst. Appl. 249:123727.Crossref, Google Scholar
• Ma S, Fildes R (2021) Retail sales forecasting with meta-learning. Eur. J. Oper. Res. 288(1):111–128.Crossref, Google Scholar
• Ma S, Fildes R, Huang T (2016) Demand forecasting with high dimensional data: The case of sku retail sales forecasting with intra-and inter-category promotional information. Eur. J. Oper. Res. 249(1):245–257.Crossref, Google Scholar
• Makridakis S, Spiliotis E, Assimakopoulos V (2022) M5 accuracy competition: Results, findings, and conclusions. Internat. J. Forecasting 38(4):1346–1364.Crossref, Google Scholar
• Mas-Colell A, Whinston MD, Green JR (1995) Microeconomic Theory (Oxford University Press, New York).Google Scholar
• McAuley J, Pandey R, Leskovec J (2015a) Inferring networks of substitutable and complementary products. Proc. 21st ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (Association for Computing Machinery, New York), 785–794.Google Scholar
• McAuley J, Targett C, Shi Q, Van Den Hengel A (2015b) Image-based recommendations on styles and substitutes. Proc. 38th Internat. ACM SIGIR Conf. Res. Development Inform. Retrieval (Association for Computing Machinery, New York), 43–52.Google Scholar
• Mišić VV, Perakis G (2020) Data analytics in operations management: A review. Manufacturing Service Oper. Management 22(1):158–169.Link, Google Scholar
• Ogaki M (1990) The indirect and direct substitution effects. Amer. Econom. Rev. 80(5):1271–1275.Google Scholar
• Oord AVD, Li Y, and, Vinyals O (2018) Representation learning with contrastive predictive coding. Preprint, submitted July 8, https://arxiv.org/abs/1807.03748.Google Scholar
• Papso R (2023) Complementary product recommendation for long-tail products. Proc. 17th ACM Conf. Recommender Systems (Association for Computing Machinery, New York), 1305–1311.Google Scholar
• Qian Y, Jiang Y, Shang J, Chai Y, Liu Y (2023) Why some products compete and others don’t: A competitive attribution model from customer perspective. Decision Support Systems 169:113956.Crossref, Google Scholar
• Rai A (2017) Editor’s comments: Diversity of design science research. MIS Quart. 41(1):iii–xviii.Crossref, Google Scholar
• Ruiz FJ, Susan A, Blei DM (2020) Shopper: A probabilistic model of consumer choice with substitutes and complements. Ann. Appl. Statist. 14(1):1–27.Crossref, Google Scholar
• Russell GJ, Ratneshwar S, Shocker AD, Bell D, Bodapati A, Degeratu A, Hildebrandt L, Kim N, Ramaswami S, Shankar VH (1999) Multiple-category decision-making: Review and synthesis. Marketing Lett. 10(3):319–332.Crossref, Google Scholar
• Sen R, Yu HF, Dhillon IS (2019) Think globally, act locally: A deep neural network approach to high-dimensional time series forecasting. Proc. 33rd Conf. Neural Information Processing Systems (Curran Associates Inc., Red Hook, NY), 4837–4846.Google Scholar
• Salinas D, Flunkert V, Gasthaus J, Januschowski T (2020) Deepar: Probabilistic forecasting with autoregressive recurrent networks. Internat. J. Forecasting 36(3):1181–1191.Crossref, Google Scholar
• Samuelson PA (1974) Complementarity: An essay on the 40th anniversary of the Hicks-Allen Revolution in Demand Theory. J. Econom. Lit. 12(4):1255–1289.Google Scholar
• Shang C, Chen J, Bi J (2021) Discrete graph structure learning for forecasting multiple time series. Proc. Internat. Conf. Learning Representations (OpenReview.net), 1–14.Google Scholar
• Shocker AD, Bayus BL, Kim N (2004) Product complements and substitutes in the real world: The relevance of “other products”. J. Marketing 68(1):28–40.Crossref, Google Scholar
• Srivastava RK, Alpert MI, Shocker AD (1984) A customer-oriented approach for determining market structures. J. Marketing 48(2):32–45.Crossref, Google Scholar
• Steinker S, Hoberg K, Thonemann UW (2017) The value of weather information for E‐commerce operations. Production Oper. Management 26(10):1854–1874.Crossref, Google Scholar
• Sun C, Adamopoulos P, Ghose A, Luo X (2022) Predicting stages in omnichannel path to purchase: A deep learning model. Inform. Systems Res. 33(2):429–445.Link, Google Scholar
• Taylor SJ, Letham B (2018) Forecasting at scale. Amer. Statist. 72(1):37–45.Crossref, Google Scholar
• Van der Maaten L, Hinton G (2008) Visualizing data using T-SNE. J. Machine Learn. Res. 9(11):2579–2605.Google Scholar
• Voleti S, Kopalle PK, Ghosh P (2015) An interproduct competition model incorporating branding hierarchy and product similarities using store-level data. Management Sci. 61(11):2720–2738.Link, Google Scholar
• Walls JG, Widmeyer GR, El Sawy OA (1992) Building an information system design theory for vigilant EIS. Inform. Systems Res. 3(1):36–59.Link, Google Scholar
• Wang L, Zhang J, Chen G Qiao D (2021) Identifying comparable entities with indirectly associative relations and word embeddings from web search logs. Decision Support Systems 141:113465.Crossref, Google Scholar
• Wilms I, Barbaglia L, Croux C (2018) Multiclass vector auto-regressive models for multistore sales data. J. Roy. Statist. Soc. C. 67(2):435–452.Crossref, Google Scholar
• Wu H, Geng C, Fang H (2024) Session-based recommendation by exploiting substitutable and complementary relationships from multi-behavior data. Data Min. Knowledge Disc. 38(3):1193–1221.Crossref, Google Scholar
• Wu L, Lin H, Tan C, Gao Z, Li SZ (2021) Self-supervised learning on graphs: Contrastive, generative, or predictive. IEEE Trans. Knowledge Data Engrg. 35(4):4216–4235.Crossref, Google Scholar
• Wu Z, Pan S, Long G, Jiang J, Chang X, and, Zhang C (2020) Connecting the dots: Multivariate time series forecasting with graph neural networks. Proc. 26th ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (Association for Computing Machinery, New York), 753–763.Google Scholar
• Yu H-F, Rao N, Dhillon IS (2016) Temporal regularized matrix factorization for high-dimensional time series prediction. Prof. 30th Conf. Neural Inform. Processing Systems (Curran Associates Inc., Red Hook, NY), 847–855.Google Scholar
• Yu B, Yin H, Zhu Z (2018) Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. Proc. 27th Internat. Joint Conf. Artificial Intelligence (ijcai.org), 3634–3640.Google Scholar
• Zhang M, Bockstedt J (2020) Complements and substitutes in online product recommendations: The differential effects on consumers’ willingness to pay. Informs. Management 57(6):103341.Crossref, Google Scholar
• Zhang W, Chen Z, Zha H, Wang J (2021a) Learning from substitutable and complementary relations for graph-based sequential product recommendation. ACM Trans. Inform. Systems 40(2):1–28.Google Scholar
• Zhang X, He Y, Brugnone N, Perlmutter M, Hirn M (2021b) Magnet: A neural network for directed graphs. Proc. 34th Adv. Neural Inform. Processing Systems 27003–27015.Google Scholar
• Zhou T, Momma M, Dong C, Yang F, Guo C, Shang J, Liu JK (2023) Multi-task learning on heterogeneous graph neural network for substitute recommendation. Proc. 29th ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (Association for Computing Machinery, New York), 1–5.Google Scholar
• Zhu H, Samtani S, Brown R, Chen H (2021a) A deep learning approach for recognizing activity of daily living (adl) for senior care: Exploiting interaction dependency and temporal patterns. MIS Quart. 45(2):859–896.Crossref, Google Scholar
• Zhu Y, Xu Y, Yu F, Liu Q, Wu S, and, Wang L (2021b) Graph contrastive learning with adaptive augmentation. Proc. Web Conf. (ACM, New York), 2069–2080.Google Scholar