Presentation | 2018-06-13 Data Analysis for Market Places by Non-negative Matrix Factorization and MDL Criterion Yosuke Arano, Yusuke Miyake, Masanori Kawakita, Jun'ichi Takeuchi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The rank selection method for non-negative matrix factorization (NMF) based on MDL criterion which was proposed by [Yamauchi et al., 2012], is applied to user action data of market places. Yamauchi et al. proposed an MDL criterion for NMF in their research for detection of cooperative actions of hosts infected with single malware, and successfully applied their NMF with the MDL criterion to real traffic data. In this paper, we apply their method to user action data of hand made market ``minne'' for the purpose of recommendation of items on sale. Minne deals various hand made products, for each of which there are a few identical items. Hence it is expected that usual recommendation method based on such as simple cooperative filters is not effective and that NMF based clustering helps. However, in our trial experiments, we did not find useful clusters for recommendation, but many clusters consists of users who try to make particular items look like more popular than they actually are. Seeing this results, we study the property of such users and develop an engine to detect them. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Non-negative Matrix Factorization / MDL criterion / market place / recommendation |
Paper # | IBISML2018-8 |
Date of Issue | 2018-06-06 (IBISML) |
Conference Information | |
Committee | NC / IBISML / IPSJ-BIO / IPSJ-MPS |
---|---|
Conference Date | 2018/6/13(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Okinawa Institute of Science and Technology |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Machine Learning Approach to Biodata Mining, and General |
Chair | Yutaka Hirata(Chubu Univ.) / Hisashi Kashima(Kyoto Univ.) |
Vice Chair | Hayaru Shouno(UEC) / Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo) |
Secretary | Hayaru Shouno(Nagoya Univ.) / Masashi Sugiyama(NAIST) / Koji Tsuda(Nagoya Inst. of Tech.) / (AIST) |
Assistant | Keiichiro Inagaki(Chubu Univ.) / Takashi Shinozaki(NICT) / Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.) |
Paper Information | |
Registration To | Technical Committee on Neurocomputing / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Bioinformatics and Genomics / Special Interest Group on Mathematical Modeling and Problem Solving |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Data Analysis for Market Places by Non-negative Matrix Factorization and MDL Criterion |
Sub Title (in English) | |
Keyword(1) | Non-negative Matrix Factorization |
Keyword(2) | MDL criterion |
Keyword(3) | market place |
Keyword(4) | recommendation |
1st Author's Name | Yosuke Arano |
1st Author's Affiliation | Kyushu University(Kyushu Univ.) |
2nd Author's Name | Yusuke Miyake |
2nd Author's Affiliation | GMO Pepabo, Inc.(GMO Pepabo) |
3rd Author's Name | Masanori Kawakita |
3rd Author's Affiliation | Kyushu University(Kyushu Univ.) |
4th Author's Name | Jun'ichi Takeuchi |
4th Author's Affiliation | Kyushu University(Kyushu Univ.) |
Date | 2018-06-13 |
Paper # | IBISML2018-8 |
Volume (vol) | vol.118 |
Number (no) | IBISML-81 |
Page | pp.pp.53-60(IBISML), |
#Pages | 8 |
Date of Issue | 2018-06-06 (IBISML) |