This study aims to build a support method for consulting service companies allowing them to respond to client demands regardless of the expertise of the consultants. With an emphasis on the revitalization of small and medium-sized enterprises, the importance of support systems for consulting services for small and medium-sized enterprises, which support solving problems that are difficult to deal with by an enterprise, is increasing. Consulting companies can respond to a wide range of management consultations; however, because the contents of a consultation are widely and highly specialized, a service proposal and the problem detection depend on the experience and intuition of the consultant, and thus a stable service may occasionally not be provided. Therefore, a support system for providing stable services independent of the ability of consultants is desired. In this research, as the first step in constructing a support system, an analysis of customer information describing the content of a consultation with the client companies is conducted to predict the occurrence of future problems. Text data such as the consultant’s visitation history, consultation content by e-mail, and call center content are used in the analysis because the contents explain not only the current problems but also possibly contain future problems. This paper describes a method for analyzing the text data by employing text mining. In the proposed method, by combining a correspondence analysis with a DEA (Data Envelopment Analysis) discriminant analysis, words that are strongly related to problem detection are extracted from a large number of words obtained from text data, and variables of the DEA discriminant analysis are reduced and analyzed. The proposed method focuses on a cancellation of contract problems. The cancellation problem does not include uncertainty; it is clearly known whether the contract of the consulting service is being updated or cancelled. In this study, computer experiments were conducted to verify the effectiveness of the proposed method through a comparison with an existing method. The results of the verification experiment are as follows. First, there is a possibility of discovering new factors that cannot be determined from the intuition and experience of the consultant regarding the target problem. Second, through a comparison with the existing method, the effectiveness of the proposed method was confirmed.

1. [1] “Small and Medium Enterprise Charter,” 2010.
2. [2] The Small and Medium Enterprise Agency, http://www.chusho.meti.go.jp/sme_english/index.html [Accessed June 25, 2018]
3. [3] “White Paper on Small and Medium Enterprises in Japan,” 2017.
4. [4] K. Hori, “What is consulting,” PHP Institute, 2011.
5. [5] F. Duan, M. Morioka, J. T. 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, 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, 2007 (in Japanese).
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.16, pp. 918-925, 2015.
13. [13] H. Murai and A. Tokosumi, “Network Analysis of the Four Gospels and the Catechism of the Catholic Church,” Vol.11, No.7, pp. 772-779, 2007.
14. [14] M. A. Clatworthy and M. J. Jones, “Financial reporting of good news and bad news: evidence from accounting narratives,” Accounting and Business Research, Vol.33, No.3, pp. 171-185, 2006.
15. [15] K. Izumi, T. Goto, and F. Matsui, “Long-term Financial Market Analysis Using Economic Textual Information,” Information Processing Society J., Vol.52, No.12, pp. 3309-3315, 2011 (in Japanese).
16. [16] MeCab: Yet Another Part-of-Speech and Morphological Analyzer (in Japanese). http://taku910.github.io/mecab/ [Accessed June 25, 2018]
17. [17] S. Shida, T. Maeda, and M. Yamazaki, “Statistical Input for Language Research Gate,” Kuroshio Publishing, 2010 (in Japanese).
18. [18] T. Sueyoshi, “DEA-discriminant analysis in the view of goal programming,” European J. of Operational Research, Vol.115, No.3, pp. 564-582, 1999.
19. [19] G. Salton and C. Buckley, “Term-weighing approaches in automatic text retrieval,” Information Processing & Management, Vol.24, No.5, pp. 513-523, 1988.