This study was conducted to devise a method for supporting consulting service companies in their response to client demands irrespective of the expertise of consultants. With emphasis on revitalization of small and medium-sized enterprises, the importance of support systems for consulting services to serve them is increasing. Those systems must support solutions to difficulties that must be addressed by enterprises. Consulting companies can respond to widely various management consultations. Nevertheless, because the consultation contents are highly specialized, service proposals and problem detection depend on the experience and intuition of the consultant. Often, stable service cannot be provided. A support system must provide stable services independent of the ability of consultants. In this study, analyzing customer information describing the contents of consultation with client companies is the first step in constructing a support system that can predict future problems. Text data such as a consultant’s visit history, consultation contents by e-mail, and contents of call centers are used for analyses because the contents can explain current problems. They might also indicate future problems. This report describes a method to analyze text data using text mining. The target problem is fraud, which includes uncertainty: cases in which it is not clear whether a fraud problem has occurred with the company. To address uncertainty, a method of using logistic regression models is proposed to represent inferred values as probabilities, rather than as binary discriminated data, because the possibility exists that some misidentified companies might have some difficulty. As described herein, computer experiments are conducted to verify the effectiveness of the proposed method and to compare consultants’ forecasted and achieved results. Results of a verification experiment are presented in the following. First, the proposed method is applicable to problems including uncertainties. Secondly, the possibility exists of discovering companies with a fraud problem of which they are unaware.

1. [1] “Small and Medium Enterprise Charter,” 2010.
2. [2] http://www.chusho.meti.go.jp/sme_english/index.html [Accessed August 13, 2020]
3. [3] “White Paper on Small and Medium Enterprises in Japan,” 2017.
4. [4] K. Hori, “What is consulting,” PHP, 2011.
5. [5] F. Duan, M. Morioka, J. Too, C. Tan, and T. Arai, “Multi-Modal Assembly Support System for Cell Production,” Int. J. Automation Technol., Vol.2, No.5, pp. 384-389, 2008.
6. [6] T. Kamma, T. Saito, and S. Abe, “Analysis and Adaptation for Exaggeration Types of Animation Motion,” Graphic Science, Vol.47, pp. 13-23, 2013.
7. [7] T. Nasukawa, “Technology using text mining / Technology to make – essence and application derived from basic technology and application examples,” Tokyo Denki University Press, 2006 (in Japanese).
8. [8] H. Wakimori, “Text Mining Techniques for Analyzing Big Data,” UNISYS Technology Review, Vol.115, pp. 337-349, 2013.
9. [9] H. T. P. Thanh and P. Meesad, “Stock Market Trend Prediction Based on Text Mining of Corporate Web and Time Series Data,” J. Adv. Comput. Intell. Intell. Inform., Vol.18, No.1, pp. 22-31, 2014.
10. [10] J. Yano and K. Araki, “Performance Evaluation for a Method of Generating Business Reports from Call Center Speech Dialogues Using Inductive Learning,” Information Processing Society of Japan SIG Technical Report, 2007.
11. [11] H. Takase, H. Kawanaka, and S. Tsuruoka, “Supporting System for Quiz in Large Class – Automatic Keyword Extraction and Browsing Interface –,” J. Adv. Comput. Intell. Intell. Inform., Vol.19, No.1, pp. 152-157, 2015.
12. [12] M. Nii, K. Takahama, and S. Miyake, “Rule Representation for Nursing-Care Process Evaluation Using Decision Tree Techniques,” J. Adv. Comput. Intell. Intell. Inform., Vol.18, No.6, pp. 918-925, 2014.
13. [13] H. Murai and A. Tokosumi, “Network Analysis of the Four Gospels and the Catechism of the Catholic Church,” J. Adv. Comput. Intell. Intell. Inform., Vol.11, No.7, pp. 772-779, 2007.
14. [14] M. J. Jones and M. Clatworthy, “Financial reporting of good news and bad news: evidence from accounting narratives,” Accounting and Business Research, Vol.33, pp. 171-185, 2003.
15. [15] K. Izumi, T. Goto, and F. Matsui, “Long-term market trend estimation using economic text information,” Information Processing Society of Japan J., Vol.52, No.12, pp. 3309-3315, 2011 (in Japanese).
16. [16] R. Watanabe, N. Fujii, D. Kokuryo, T. Kaihara, Y. Abe, and R. Santo, “A Study of Supporting Method of Consulting Service using text mining,” Int. J. Automation Technol., Vol.12, No.4, pp. 482-491, 2018.
17. [17] R. Watanabe, N. Fujii, D. Kokuryo, T. Kaihara, and Y. Abe, “Application of support systems for consulting service to real problem using a synonym dictionary,” Acta Electrotechnnica et Informatica, Vol.20, No.2, pp. 3-10, 2020.
18. [18] http://taku910.github.io/mecab/ (in Japanese) [Accessed August 13, 2020]
19. [19] S. Shida, T. Maeda, and M. Yamazaki, “Statistical Input for Language Research Gate,” Kuroshio Publishing, 2010 (in Japanese).
20. [20] T. Sueyoshi, “DEA-discriminant analysis in the view of goal programming,” European J. of Operational Research, Vol.115, pp. 564-582, 1999.