Lineer regresyon ile NLP uygulamasının müşteri kaybı analizine adaptasyonu

Year 2021, , 399 - 408, 31.12.2021

Emre S. Özmen

https://doi.org/10.31590/ejosat.1002211

Abstract

Müşteri kaybı tahmini çalışmanın önünde muhtelif engeller vardır. Birincisi, salt pozitif bilim alanından farklı olarak, iş dünyasının doğası gerçek bir veri bulma olasılığını sınırlamaktadır. Başka bir deyişle iş dünyasında daha fazla veri düzenleyici bulunmakta, yükümlülükler paylaşılmasını giderek zorlaştırmakta ama buna mukabil bulguların pratikliği daha anlamlı hale gelmektedir. Buna tezat teşkil edecek bir şekilde, NPO'lar tarafından daha fazla veri (örneğin, "ünlü" Iris çiçeği veri kümesi) sağlanabilmekte, dolayısı ile bu verilerin toplanması daha olası hale gelmekte, ancak bilginin kullanılabilirliği azalmaktadır. Bu çalışma ile, sınırlı veriye rağmen, dört öneri oluşturulmuş ve uygulamaları sergilenmiştir. Kazanan model, sınıflandırma performans üçlüsünün her birinde, doğruluk, kesinlik ve geri çağırmada çift haneli iyileştirme sağlamıştır.

Keywords

Müşteri Kaybı, Churn, NLP, Regression

Challenging implicit bias: An application of linear regression with NLP for churn prediction

Abstract

The problems with working in churn prediction are twofold. First, unlike pure science, the practical applications of data in the business world limit the probability of collecting real data—that is, more data is subject to big data, more regulative liabilities in the real business world occur. These results in data collection becoming more challenging despite the increased practicality of the findings. Moreover, since more data (e.g., the Iris flower dataset) is being provided by NPOs, it is becoming more probable, although the usability of the data has decreased. This study introduces unique ideas by placing inceptions within typical stages of churn prediction. As part of this study, four proposals were generated and applied, and the winning model was challenged with double-digit improvement in each aspect of the classification performance trio—namely accuracy, precision, and recall.

Keywords

Churn predictions, NLP optimizations, Recall favoring systems, Linear regression as classifier

References

• Fayyad, Piatetsky-Shapiro, & Smyth. (1996). From Data Mining to Knowledge Discovery: An Overview, in Fayyad, Piatetsky-Shapiro, Smyth, & Uthurusamy, Advances in Knowledge Discovery and Data Mining. AAAI Press / MIT Press. 1–34.
• Kabasakal, İ . (2020). Customer Segmentation Based On Recency Frequency Monetary Model: A Case Study in E-Retailing . Bilişim Teknolojileri Dergisi , 13 (1) , 47-56 . DOI: 10.17671/gazibtd.570866
• Peng, Y., Kou, G., Shi, Y., & Chen, Z. (2008). A descriptive framework for the field of data mining and knowledge discovery. International Journal of Information Technology & Decision Making, 7(04), 639–682.
• Özmen, M , Delice, Y , Kızılkaya Aydoğan, E . (2018). Telekomünikasyon Sektöründe PSO ile Müşteri Bölümlemesi . Bilişim Teknolojileri Dergisi , 11 (2) , 163-173 . DOI: 10.17671/gazibtd.368460
• Karahoca, A., Karahoca, D., & Aydin, N. (2007). GSM Churn Management Using an Adaptive Neuro-Fuzzy Inference System. The 2007 International Conference on Intelligent Pervasive Computing (IPC 2007), 323-326.
• Huang, B., Kechadi, M. T., & Buckley, B. (2012). Customer churn prediction in telecommunications. Expert Systems with Applications, 39(1), 1414–1425.
• KDD (2018). KDD Cup 2009: Customer relationship prediction. https://www.kdd.org/kdd-cup/view/kdd-cup-2009
• Xiao, J., Jiang, X., He, C., & Teng, G. (2016). Churn prediction in customer relationship management via GMDH-based multiple classifiers ensemble. IEEE Intelligent Systems, 31(2), 37–44.
• Au, W. H., Chan, K. C., & Yao, X. (2003). A novel evolutionary data mining algorithm with applications to churn prediction. IEEE transactions on evolutionary computation, 7(6), 532–545.
• Lu, N., Lin, H., Lu, J., & Zhang, G. (2012). A customer churn prediction model in telecom industry using boosting. IEEE Transactions on Industrial Informatics, 10(2), 1659–1665.
• Niculescu-Mizil, A., Perlich, C., Swirszcz, G., Sindhwani, V., Liu, Y., Melville, P., Wang, D., Xiao, J., Hu, J., Singh, M., Shang, W., Zhu, Y. (2009). Winning the KDD cup orange challenge with ensemble selection. The 2009 Knowledge Discovery in Data Competition. 23–34.
• Lango,M.(2019).Tackling the Problem of Class Imbalance in Multi-class Sentiment Classification: An Experimental Study. Foundations of Computing and Decision Sciences,44(2) 151-178. https://doi.org/10.2478/fcds-2019-0009
• Olson, R. S., Bartley, N., Urbanowicz, R. J., & Moore, J. H. (2016, July). Evaluation of a tree-based pipeline optimization tool for automating data science. In Proceedings of the Genetic and Evolutionary Computation Conference. 485–492.
• Yao, Q., Wang, M., Chen, Y., Dai, W., Li, Y. F., Tu, W. W., ... & Yu, Y. (2018). Taking human out of learning applications: A survey on automated machine learning. arXiv preprint arXiv:1810.13306.
• Chen, Y. W., Song, Q., & Hu, X. (2021). Techniques for automated machine learning. ACM SIGKDD Explorations Newsletter, 22(2), 35–50.
• H2O.ai, H2O AutoML. (2017). http://docs.h2o.ai/h2o/latest-stable/h2o-docs/automl.html. H2O version 3.30.0.1.
• Drozdal, J., Weisz, J., Wang, D., Dass, G., Yao, B., Zhao, C., ... & Su, H. (2020, March). Trust in automl: Exploring information needs for establishing trust in automated machine learning systems. In Proceedings of the 25th International Conference on Intelligent User Interfaces. 297–307.
• LeDell, E. (2018). The different flavors of AutoML. https://www.h2o.ai/blog/the-different-flavors-of-automl/
• Lee, D. J. L., Macke, S., Xin, D., Lee, A., Huang, S., & Parameswaran, A. G. (2019). A Human-in-the-loop Perspective on AutoML: Milestones and the Road Ahead. IEEE Data Eng. Bull., 42(2), 59–70.
• Gürsakal, N. , Gürsakal, S. & Çelik, S. (2021). Big Data Companies and Open Source Movement . Avrupa Bilim ve Teknoloji Dergisi , (21) , 680-689 . Retrieved from https://dergipark.org.tr/en/pub/ejosat/issue/59648/822219
• Miner, G., Delen, D., Elder, J., Fast, A., Hill, T., & Nisbet, R. (2012). The seven practice areas of text analytics. In Practical text mining and statistical analysis for non-structured text data applications. 29–41.
• Wang, C., & Wu, Q. (2019). Flo: Fast and lightweight hyperparameter optimization for automl. arXiv preprint arXiv:1911.04706.
• Blohm, M., Hanussek, M., & Kintz, M. (2020). Leveraging Automated Machine Learning for Text Classification: Evaluation of AutoML Tools and Comparison with Human Performance. arXiv preprint arXiv:2012.03575.
• Data Science, ADS, Text Mining, Page 1, Columbia University Engineering School & Emeritus.
• Fan, W., Wallace, L., Rich, S., & Zhang, Z. (2006). Tapping the power of text mining. Communications of the ACM, 49(9), 76–82.
• Lee, S., Song, J., & Kim, Y. (2010). An empirical comparison of four text mining methods. Journal of Computer Information Systems, 51(1), 1–10.