Abstract
We propose a new topic model for analyzing purchase data with price information. Price is an important factor in consumer purchase behavior. The proposed model assumes that a topic has its own price distributions for each item as well as an item distribution. The topic proportions, which represent a user’s purchase tendency, are influenced by the user’s purchased items and their prices. By estimating the mean and the variance of the price for each topic, the proposed model can cluster related items taking their price ranges into consideration. We present its efficient inference procedure based on collapsed Gibbs sampling. Experiments on real purchase data demonstrate the effectiveness of the proposed model.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Blei DM, Jordan MI (2003) Modeling annotated data. In: SIGIR ’03, pp 127–134
Blei DM, Lafferty JD (2006) Dynamic topic models. In: ICML ’06, pp 113–120
Blei DM, Ng AY, Jordan MI (2003) Latent Dirichlet allocation. J Mach Learn Res 3: 993–1022
Das AS, Datar M, Garg A, Rajaram S (2007) Google news personalization: scalable online collaborative filtering. In: WWW ’07, pp 271–280
Fu W, Song L, Xing EP (2009) Dynamic mixed membership block model for evolving networks. In: ICML ’09, pp 329–336
Griffiths TL, Steyvers M (2004) Finding scientific topics. Proc Nat Acad Sci 101(1):5228–5235
Hamuro Y, Katoh N, Matsuda Y, Yada K (1998) Mining pharmacy data helps to make profits. Data Min Knowl Disc 2(4): 391–398
Hofmann T (1999) Probabilistic latent semantic analysis. In: UAI ’99, pp 289–296
Hofmann T (2003) Collaborative filtering via Gaussian probabilistic latent semantic analysis. In: SIGIR ’03. ACM Press, New York, pp 259–266
Hoffman M, Blei D, Bach F (2010) Online learning for latent Dirichlet allocation. In: NIPS ’10
Iwata T, Saito K, Yamada T (2006) Recommendation methods for extending subscription periods. In: KDD ’06, pp 574–579
Iwata T, Watanabe S, Yamada T, Ueda N (2009) Topic tracking model for analyzing consumer purchase behavior. In: IJCAI ’09, pp 1427–1432
Iwata T, Yamada T, Sakurai Y, Ueda N (2010) Online multiscale dynamic topic models. In: KDD ’10, pp 663–672
Jin X, Zhou Y, Mobasher B (2004) Web usage mining based on probabilistic latent semantic analysis. In: KDD ’04, pp 197–205
Li M, Dias BM, Jarman I, El-Deredy W, Lisboa PJ (2009) Grocery shopping recommendations based on basket-sensitive random walk. In: KDD ’09, pp 1215–1224
Mimno D, Wallach HM, Naradowsky J, Smith DA, McCallum A (2009) Polylingual topic models. In: EMNLP ’09, pp 880–889
Minka T (2000) Estimating a Dirichlet distribution. Technical report. MIT, Cambridge
Minka T, Lafferty J (2002) Expectation-propagation for the generative aspect model. In: UAI ’02, pp 352–359
Newman D, Asuncion A, Smyth P, Welling M (2007) Distributed inference for latent Dirichlet allocation. In: NIPS ’07, pp 1081–1088
Nijs VR, Dekimpe MG, Steenkamps JBE, Hanssens DM (2001) The category-demand effects of price promotions. Market Sci 20(1): 1–22
Raju JS (1992) The effect of price propotion on variability in product category sales. Market Sci 11(3): 207–220
Rosen-Zvi M, Griffiths T, Steyvers M, Smyth P (2004) The author-topic model for authors and documents. In: UAI ’04, pp 487–494
Sato I, Kurihara K, Nakagawa H (2010) Deterministic single-pass algorithm for lda. In: NIPS ’10
Shani G, Heckerman D, Brafman RI (2005) An MDP-based recommender system. J Mach Learn Res 6: 1265–1295
Teh YW, Jordan MI, Beal MJ, Blei DM (2006) Hierarchical Dirichlet processes. J Am Stat Assoc 101(476): 1566–1581
Teh YW, Newman D, Welling M (2006) A collapsed variational Bayesian inference algorithm for latent Dirichlet allocation. In: NIPS ’06, 1378–1385
Thomas S, Chakravarthy S. (2000) Incremental mining of constrained associations. In: HIPC ’00, 547–558
Wallach HM (2006) Topic modeling: Beyond bag-of-words. In: ICML ’06, 977–984
Wang X, McCallum A (2006) Topics over time: a non-Markov continuous-time model of topical trends. In: KDD ’06, 424–433
Williamson S, Wang C, Heller K, Blei D (2010) The IBP-compound dirichlet process and its application to focused topic modeling. In: ICML ’10, 1151–1158
Author information
Authors and Affiliations
Corresponding author
Additional information
Responsible editor: Bing Liu.
Rights and permissions
About this article
Cite this article
Iwata, T., Sawada, H. Topic model for analyzing purchase data with price information. Data Min Knowl Disc 26, 559–573 (2013). https://doi.org/10.1007/s10618-012-0281-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10618-012-0281-y