{"type":"ScholarlyArticle","title":"App Download Forecasting: An Evolutionary Hierarchical Competition Approach","authors":[{"name":"Yingzi Wang","slug":"yingzi-wang","given":"Yingzi","family":"Wang","affiliation":"University of Melbourne"},{"name":"Nicholas Jing Yuan","slug":"nicholas-jing-yuan","given":"Nicholas Jing","family":"Yuan","affiliation":"University of Melbourne"},{"name":"Yu Sun","slug":"yu-sun","given":"Yu","family":"Sun","affiliation":"‡ Microsoft Corporation"},{"name":"Chuan Qin","slug":"chuan-qin","given":"Chuan","family":"Qin","affiliation":"University of Melbourne"},{"name":"Xing Xie","slug":"xing-xie","given":"Xing","family":"Xie","affiliation":"† ⋆ University of Science and Technology of China Microsoft Research ♯"}],"abstract":"Product sales forecasting enables comprehensive understanding of products' future development, making it of particular interest for companies to improve their business, for investors to measure the values of firms, and for users to capture the trends of a market. Recent studies show that the complex competition interactions among products directly influence products' future development. However, most existing approaches fail to model the evolutionary competition among products and lack the capability to organically reflect multi-level competition analysis in sales forecasting. To address these problems, we propose the Evolutionary Hierarchical Competition Model (EHCM), which effectively considers the time-evolving multi-level competition among products. The EHCM model systematically integrates hierarchical competition analysis with multi-scale time series forecasting. Extensive experiments using a real-world app download dataset show that EHCM outperforms state-of-the-art methods in various forecasting granularities.","doi":"10.24963/ijcai.2017/415","url":"https://ijcai.org/proceedings/2017/415","pdf":"https://ijcai.org/proceedings/2017/0415.pdf","markdown":"https://ijcai.org/proceedings/2017/415.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/415","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Machine Learning S-Z","track":"Main track","number":415,"pages":{"first":2978,"last":2984},"keywords":["Machine Learning: Time-series/Data Streams","Machine Learning: Data Mining"],"videos":[],"references":[{"position":1,"raw":"[Begon et al., 2005] Michael Begon, Colin R Townsend, and John Lander Harper. From individuals to ecosystems. Blackwell Publishers Hoboken, 2005.","title":"From individuals to ecosystems","authors":"Michael Begon, Colin R Townsend, John Lander Harper","year":"2005","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Berrocal et al., 2010] Veronica J Berrocal, Adrian E Raftery, Tilmann Gneiting, and Richard C Steed. Probabilistic weather forecasting for winter road mainte- nance. Journal of the American Statistical Association, 105(490):522-537, 2010.","title":"Probabilistic weather forecasting for winter road maintenance","authors":"J Veronica, Adrian E Berrocal, Tilmann Raftery, Richard C Gneiting, Steed","year":"2010","venue":"Journal of the American Statistical Association","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Briand and Cohen, 1987] Frederic Briand and Joel E Co- hen. Environmental correlates of food chain length. Sci- ence, 238(4829):956-961, 1987.","title":"Environmental correlates of food chain length","authors":"Cohen Briand, Joel E Cohen","year":"1987","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Brockwell and Davis, 2016] Peter J Brockwell and Richard A Davis. Introduction to time series and forecasting. springer, 2016.","title":"Introduction to time series and forecasting","authors":"J Peter, Richard A Brockwell, Davis","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chandra and Zhang, 2012] Rohitash Chandra and Mengjie Zhang. Cooperative coevolution of elman recurrent neural networks for chaotic time series prediction. Neurocomput- ing, 86:116-123, 2012.","title":"Cooperative coevolution of elman recurrent neural networks for chaotic time series prediction","authors":"Chandra, Zhang, Rohitash Chandra, Mengjie Zhang","year":"2012","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dunlavy et al., 2011] Daniel M Dunlavy, Tamara G Kolda, and Evrim Acar. Temporal link prediction using matrix and tensor factorizations. TKDD, 5(2):10, 2011.","title":"Temporal link prediction using matrix and tensor factorizations","authors":"Tamara G Daniel M Dunlavy, Evrim Kolda, Acar","year":"2011","venue":"TKDD","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ernst et al., 2007] Floris Ernst, Alexander Schlaefer, and Achim Schweikard. Prediction of respiratory motion with wavelet-based multiscale autoregression. In International Conference on Medical Image Computing and Computer- Assisted Intervention, pages 668-675. Springer, 2007.","title":"Prediction of respiratory motion with wavelet-based multiscale autoregression","authors":"Ernst","year":"2007","venue":"International Conference on Medical Image Computing and Computer-Assisted Intervention","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Fu, 2011] Tak-chung Fu. A review on time series data min- ing. Engineering Applications of Artificial Intelligence, 24(1):164-181, 2011.","title":"A review on time series data mining","authors":"Tak-Chung Fu","year":"2011","venue":"Engineering Applications of Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Garber et al., 2004] Tal Garber, Jacob Goldenberg, Barak Libai, and Eitan Muller. From density to destiny: Using spatial dimension of sales data for early prediction of new product success. Marketing Science, 23(3):419-428, 2004.","title":"From density to destiny: Using spatial dimension of sales data for early prediction of new product success","authors":"Garber","year":"2004","venue":"Marketing Science","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Himberg et al., 2001] Johan Himberg, Kalle Korpiaho, Heikki Mannila, Johanna Tikanmaki, and Hannu TT Toivonen. Time series segmentation for context recogni- tion in mobile devices. In Data Mining, 2001. ICDM 2001, pages 203-210. IEEE, 2001.","title":"Time series segmentation for context recognition in mobile devices","authors":"Johan Himberg, Kalle Korpiaho, Heikki Mannila, Johanna Tikanmaki, Hannu Tt Toivonen","year":"2001","venue":"Data Mining","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Huisman and Weissing, 1999] Jef Huisman and Franz J Weissing. Biodiversity of plankton by species oscillations and chaos. Nature, 402(6760):407-410, 1999.","title":"Biodiversity of plankton by species oscillations and chaos","authors":"Weissing Huisman, Jef Huisman, Franz J Weissing","year":"1999","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hyndman et al., 2007] Rob J Hyndman, Yeasmin Khan- dakar, et al. Automatic time series for forecasting: the forecast package for r. Technical report, Monash Univer- sity, Department of Econometrics and Business Statistics, 2007.","title":"Automatic time series for forecasting: the forecast package for r","authors":"Rob J Hyndman, Yeasmin Khandakar","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Johnson et al., 2013] Dominic DP Johnson, Michael E Price, and Mark Van Vugt. Darwin's invisible hand: Mar- ket competition, evolution and the firm. Journal of Eco- nomic Behavior & Organization, 90:S128-S140, 2013.","title":"Darwin's invisible hand: Market competition, evolution and the firm","authors":"Dominic Dp Johnson, Michael E Price, Mark Van Vugt","year":"2013","venue":"Journal of Economic Behavior & Organization","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kahn, 2010] Kenneth B Kahn. New-Product Forecasting. Wiley Online Library, 2010.","title":"New-Product Forecasting","authors":"Kenneth B Kahn","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Levine, 1976] Stephen H Levine. Competitive interactions in ecosystems. The American Naturalist, 110(976):903- 910, 1976.","title":"Competitive interactions in ecosystems","authors":"Stephen H Levine","year":"1976","venue":"The American Naturalist","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liao et al., 2012] Zhung-Xun Liao, Po-Ruey Lei, Tsu-Jou Shen, Shou-Chung Li, and Wen-Chih Peng. Mining tem- poral profiles of mobile applications for usage prediction. In Data Mining Workshops (ICDMW), 2012 IEEE, pages 890-893. IEEE, 2012.","title":"Mining temporal profiles of mobile applications for usage prediction","authors":"Zhung-Xun Liao, Po-Ruey Lei, Tsu-Jou Shen, Shou-Chung Li, Wen-Chih Peng","year":"2012","venue":"Data Mining Workshops (ICDMW)","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Matsubara et al., 2012] Yasuko Matsubara, Yasushi Saku- rai, Christos Faloutsos, Tomoharu Iwata, and Masatoshi Yoshikawa. Fast mining and forecasting of complex time- stamped events. In Proceedings of the 18th ACM SIGKDD, pages 271-279. ACM, 2012.","title":"Fast mining and forecasting of complex timestamped events","authors":"Yasuko Matsubara, Yasushi Sakurai, Christos Faloutsos, Tomoharu Iwata, Masatoshi Yoshikawa","year":"2012","venue":"Proceedings of the 18th ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Percival and Walden, 2006] Donald B Percival and An- drew T Walden. Wavelet methods for time series analysis, volume 4. Cambridge university press, 2006.","title":"Wavelet methods for time series analysis","authors":"B Donald, Andrew T Percival, Walden","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Radosavljevic et al., 2016] Vladan Radosavljevic, Mihajlo Grbovic, Nemanja Djuric, Narayan Bhamidipati, Daneo Zhang, Jack Wang, Jiankai Dang, Haiying Huang, Ananth Nagarajan, and Peiji Chen. Smartphone app categorization for interest targeting in advertising marketplace. In Pro- ceedings of the 25th International Conference Companion on WWW, pages 93-94, 2016.","title":"Smartphone app categorization for interest targeting in advertising marketplace","authors":"Vladan Radosavljevic, Mihajlo Grbovic, Nemanja Djuric, Narayan Bhamidipati, Daneo Zhang, Jack Wang, Jiankai Dang, Haiying Huang, Ananth Nagarajan, Peiji Chen","year":"2016","venue":"Proceedings of the 25th International Conference Companion on WWW","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Renaud et al., 2005] Olivier Renaud, J-L Starck, and Fionn Murtagh. Wavelet-based combined signal filtering and prediction. IEEE Transactions on Systems, Man, and Cy- bernetics, Part B (Cybernetics), 35(6):1241-1251, 2005.","title":"Wavelet-based combined signal filtering and prediction","authors":"Olivier Renaud, J-L Starck, Fionn Murtagh","year":"2005","venue":"IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Rogers et al., 2013] Mark Rogers, Lei Li, and Stuart J Rus- sell. Multilinear dynamical systems for tensor time series. In Advances in Neural Information Processing Systems, pages 2634-2642, 2013.","title":"Multilinear dynamical systems for tensor time series","authors":"Mark Rogers, Lei Li, Stuart J Russell","year":"2013","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Sadilek and Krumm, 2012] Adam Sadilek and John Krumm. Far out: Predicting long-term human mobility. In AAAI, 2012.","title":"Far out: Predicting long-term human mobility","authors":"Krumm Sadilek, Adam Sadilek, John Krumm","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Sahney et al., 2010] Sarda Sahney, Michael J Benton, and Paul A Ferry. Links between global taxonomic diversity, ecological diversity and the expansion of vertebrates on land. Biology letters, 6(4):544-547, 2010.","title":"Links between global taxonomic diversity, ecological diversity and the expansion of vertebrates on land","authors":"Sarda Sahney, Michael J Benton, Paul A Ferry","year":"2010","venue":"Biology letters","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Soltani, 2002] Skander Soltani. On the use of the wavelet decomposition for time series prediction. Neurocomput- ing, 48(1):267-277, 2002.","title":"On the use of the wavelet decomposition for time series prediction","authors":"Skander Soltani","year":"2002","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wu and Brynjolfsson, 2014] Lynn Wu and Erik Brynjolfs- son. The future of prediction: How google searches fore- shadow housing prices and sales. In Economic analysis of the digital economy, pages 89-118. 2014.","title":"The future of prediction: How google searches foreshadow housing prices and sales","authors":"Lynn Wu, Erik Brynjolfsson","year":"2014","venue":"Economic analysis of the digital economy","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yu et al., 2010] Xiaohui Yu, Yang Liu, Xiangji Huang, and Aijun An. A quality-aware model for sales prediction using reviews. In Proceedings of the 19th international conference on World wide web, pages 1217-1218. ACM, 2010.","title":"A quality-aware model for sales prediction using reviews","authors":"Xiaohui Yu, Yang Liu, Xiangji Huang, Aijun An","year":"2010","venue":"Proceedings of the 19th international conference on World wide web","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhuang et al., 2013] Fuzhen Zhuang, Ping Luo, Changying Du, Qing He, and Zhongzhi Shi. Triplex transfer learning: exploiting both shared and distinct concepts for text clas- sification. In Proceedings of the sixth ACM ICWSM, pages 425-434. ACM, 2013.","title":"Triplex transfer learning: exploiting both shared and distinct concepts for text classification","authors":"Zhuang","year":"2013","venue":"Proceedings of the sixth ACM ICWSM","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}