The Research on Dynamics in Phone Sales Marketing Campaign Based on Machine Learning

Zhuoye Lai

doi:10.54691/bcpbm.v32i.2967

Authors

Zhuoye Lai

DOI:

https://doi.org/10.54691/bcpbm.v32i.2967

Keywords:

Machine Learning, Phone Sales Marketing, Portuguese bank

Abstract

Phone market campaign is one of the selling methods that banks use to attract new term deposits. Identifying attributes of customers is essential to increase the successful rate of a phone marketing campaign. This paper uses a dataset from a Portuguese bank where various features and attributes of customers are summarized. Four methods are used to analyze this issue, firstly decision tree method, then random forest method, K nearest neighbor and lastly logistic regression. After evaluating and reviewing their confusion matrices and generated scores, the decision has been made to choose the model of random forest as it possesses the highest mean of all metrics of classification. In conclusion, the duration of contact, age, how many days have passed since last contact, the month of the contact, and the number of contacts on one customer are deemed as more important than other attributes under a random forest classifier. The findings of this paper implicates that the Portuguese bank needs to focus more of these attributes to obtain a sustainable development.

Downloads

Download data is not yet available.

References

Cardone, G. When It Comes to Sales, the Phone Is Your Most Powerful Tool. Entrepreneur. Entrepreneur, April 24, 2015. https://www.entrepreneur.com/article/245434.

Li, C. Why Phone Calls Are Still The Most Effective Lead Generators, March 18, 2021. https://retreaver.com/blog/phone-calls-effective-lead-generation-strategy.

El Naqa, I., Murphy, M.J. (2015). What Is Machine Learning?. In: El Naqa, I., Li, R., Murphy, M. (eds) Machine Learning in Radiation Oncology. Springer, Cham. https://doi.org/10.1007/978-3-319-18305-3_1 DOI: https://doi.org/10.1007/978-3-319-18305-3

Oluwabusola, Oluwaseun Esther. Applying Business Analytics in Practice to a Bank Telemarketing Dataset. University of Strathclyde, September 2015. https://local.cis.strath.ac.uk/wp/extras/msctheses/papers/strath_cis_publication_2714.pdf.

Sui, A. Portuguese Bank Marketing Data Set. Kaggle, April 9, 2019. https://www.kaggle.com/datasets/yufengsui/portuguese-bank-marketing-data-set?resource=download.

Broeck, Jan Van den, Solveig Argeseanu Cunningham, Roger Eeckels, and Kobus Herbst. Data Cleaning: Detecting, Diagnosing, and Editing Data Abnormalities. PLOS Medicine. Public Library of Science. Accessed August 1, 2022. https://journals.plos.org/plosmedicine/article?id=10.1371%2Fjournal.pmed.0020267. DOI: https://doi.org/10.1371/journal.pmed.0020267

Brownlee, J. Why One-Hot Encode Data in Machine Learning? Machine Learning Mastery, June 30, 2020. https://machinelearningmastery.com/why-one-hot-encode-data-in-machine-learning/.

Jović A, K Brkić, and N Bogunović. A Review of Feature Selection Methods with Applications. ResearchGate, May 2015. https://www.researchgate.net/profile/Alan-Jovic/publication/308871570_A_review_of_feature_selection_methods_with_applications/links/62792a8db1ad9f66c8ae5cf6/A-review-of-feature-selection-methods-with-applications.pdf.

Asif, M. Predicting the Success of Bank Telemarketing Using Various Classification Algorithms. Örebro University School of Business. Accessed August 1, 2022. https://www.diva-portal.org/smash/get/diva2:675139/FULLTEXT01.pdf.

Quinlan, J. R. Learning Decision Tree Classifiers. ACM Computing Surveys 28, no. 1 (1996): 71–72. https://doi.org/10.1145/234313.234346. DOI: https://doi.org/10.1145/234313.234346

Song, Yang, Jian Huang, Ding Zhou, Hongyuan Zha, and C. Lee Giles. IKNN: Informative K-Nearest Neighbor Pattern Classification." Knowledge Discovery in Databases: PKDD 2007, n.d., 248–64. https://doi.org/10.1007/978-3-540-74976-9_25. DOI: https://doi.org/10.1007/978-3-540-74976-9_25

LaValley, Michael P. Logistic Regression. Logistic Regression. Circulation, May 6, 2008. https://www.ahajournals.org/doi/full/10.1161/CIRCULATIONAHA.106.682658. DOI: https://doi.org/10.1161/CIRCULATIONAHA.106.682658

Olugbenga, M. Balanced Accuracy: When Should You Use It? neptune.ai. neptuneblog, July 22, 2022. https://neptune.ai/blog/balanced-accuracy.

Classification: Roc Curve and AUC. Machine Learning. Accessed August 27, 2022. https://developers.google.com/machine-learning/crash-course/classification/roc-and-auc.

Biau, G, and Erwan S. A Random Forest Guided Tour. TEST 25, no. 2 (2016): 197–227. https://doi.org/10.1007/s11749-016-0481-7. DOI: https://doi.org/10.1007/s11749-016-0481-7

Wlodarczyk, K, and Kingsley I. Data Analysis of a Portuguese Marketing Campaign Using Bank Marketing ... Data Analysis of a Portuguese Marketing Campaign using Bank Marketing data Set. ResearchGate, December 5, 2019. https://www.researchgate.net/publication 339988208_Data_Analysis_of_a_Portuguese_Marketing_Campaign_using_Bank_Marketing_data_Set.

Ghosh, S. How to Compare Machine Learning Models and Algorithms. neptune.ai, July 22, 2022. https://neptune.ai/blog/how-to-compare-machine-learning-models-and-algorithms.