KMITL Expo 2026 LogoKMITL 66th Anniversary Logo

Development of Credit Card Customer Churn Prediction Model

Abstract

This report is part of applying the knowledge gained from studying machine learning models and methods for developing a predictive model to identify customers likely to cancel their credit card services with a bank. The project was carried out during an internship at a financial institution, where the creator developed a model to predict customers likely to churn from their credit card services using real customer data through the organization's system. The focus was on building a model that can accurately predict customer churn by selecting features that are appropriate for the prediction model and the unique characteristics of the credit card industry data to ensure the highest possible accuracy and efficiency. This report also covers the integration of the model into the development of a website, which allows related departments to conveniently use the prediction model. Users can upload data for prediction and receive model results instantly. In addition, a dashboard has been created to present insights from the model's predictions, such as identifying high-risk customers likely to cancel services, as well as other important analytical information for strategic decision-making. This will help support more efficient marketing planning and customer retention efforts within the organization.

Objective

บัตรเครดิตเป็นบริการอย่างหนึ่งทางการเงิน ช่วยอำนวยความสะดวกแก่ผู้ใช้สามารถชำระค่าสินค้าและบริการโดยไม่ต้องใช้เงินสด ธนาคารทำหน้าที่เป็นตัวกลางในการชำระเงินให้กับร้านค้า และเรียกเก็บเงินจากผู้ใช้บัตรในภายหลัง บัตรเครดิตของแต่ละธนาคารจึงได้รับความนิยมอย่างรวดเร็วในประเทศไทย ส่งผลให้มีการแข่งขันสูง ธนาคารต้องพัฒนากลยุทธ์เพื่อดึงดูด และรักษาลูกค้าไว้ ในการทำธุรกิจ การสูญเสียลูกค้าถือเป็นปัญหาสำคัญที่ส่งผลกระทบต่อธุรกิจทุกประเภท โดยบัตรเครดิตของธนาคารถือเป็นอีกหนึ่งธุรกิจที่ได้รับผลกระทบจากการสูญเสียลูกค้าค่อนข้างมาก เนื่องจากการเติบโตมาจากผู้ใช้บัตรเป็นหลัก ส่งผลให้ลูกค้าบัตรเครดิตมีมูลค่าสูงและสามารถสร้างรายได้ให้กับธนาคารอย่างต่อเนื่อง ธนาคารจึงจำเป็นต้องหาแนวทางและวิธีป้องกันเพื่อรักษาไม่ให้ลูกค้ายกเลิกการใช้บริการ โดยการทำนายลักษณะลูกค้าที่มีแนวโน้มจะยกเลิกการใช้บริการบัตรเครดิตเป็นแนวทางหนึ่งที่สามารถช่วยธนาคารในการแก้ไขปัญหานี้ได้ การทำนายลักษณะลูกค้าที่กำลังจะยกเลิกการใช้บริการบัตรเครดิตสามารถทำได้โดยใช้ Machine Learning Model ซึ่งสามารถวิเคราะห์ข้อมูลจำนวนมากและหาความสัมพันธ์ของข้อมูลที่ซับซ้อน ทำให้องค์กรได้รับข้อมูลเชิงลึกที่เป็นประโยชน์ในการใช้วิเคราะห์และประกอบการตัดสินใจเพื่อหาแนวทางและกลยุทธ์ที่เหมาะสมที่สุดในการรักษาและป้องกันการสูญเสียลูกค้าเพื่อรักษารายได้และเสถียรภาพขององค์กรไว้

Other Innovations

Effect of freshness preservation methods of Threadfin breams (Nemipterus furcosus) from small scale fisheries on quality for sashimi.

คณะเทคโนโลยีการเกษตร

Effect of freshness preservation methods of Threadfin breams (Nemipterus furcosus) from small scale fisheries on quality for sashimi.

Threadfin breams is an economically important fish that can be found in fisheries in both the Gulf of Thailand and Andaman Sea and is cheap. In addition, the consumption of raw fish as sashimi is increasingly popular in Thailand. Therefore, it is necessary to promote its consumption to increase its value. This study investigated the preservation of threadfin breams (N. furcosus) for raw or sashimi consumption. The preservation of threadfin breams consisted of Ikejime (K) and cold seawater (S) methods, and the preservation of the fish by Gutting (G) and whole (W) and storing for 3 days on ice (I) or in a refrigerator (F). The freshness quality of threadfin breams was evaluated by sensory, physicochemical (TVB-N, TMA-N and pH), freshness index (Ki-value) and microbiological methods. It was found that after being stored for 3 days, the KGF group of threadfin breams had the highest overall sensory score, which was 8.36±0.80 points, and the KWI, SWI and SWF groups of threadfin breams had the lowest overall sensory scores, which were 8.13±0.77, 8.13±0.77 and 8.13±0.81 points, respectively. And the overall sensory scores of all experimental groups of fish increased significantly (p<0.05). The TVB-N value of threadfin breams in KGF group had the lowest TVB-N value, which was 1.37±0.93 mg nitrogen/100 g sample. The threadfin breams in SGI group had the highest TVB-N value, which was 2.36±1.15 mg nitrogen/100 g sample. The TVB-N of fish in all experimental groups increased significantly (p<0.05). The TMA-N value of threadfin breams in KGF group had the lowest TMA-N value, which was 1.56±0.88 mg nitrogen/100 g sample. The threadfin breams in SWF group had the highest TMA-N value, which was 2.17±1.22 mg nitrogen/100 g sample. The TMA-N of fish in all experimental groups increased significantly (p<0.05). The pH value of threadfin breams in KGF group had the lowest pH value, which was 6.40±0.12. The threadfin breams in SWF group had the highest pH value, which was 6.78±0.25. The pH of fish in all experimental groups increased significantly (p<0.05). Ki value The threadfin breams in KGF group had the lowest Ki value, which was 9.05±0.73%. The threadfin breams in KWI group had the highest Ki value, which was 12.88±4.19%. The Ki value of all experimental groups of fish increased without statistical significance (p>0.05). In terms of freshness quality in microbiology, it was found that in all experimental groups, Salmonella spp., S. aureus, B. cereus, C. perfringens and E. coli were found in all experimental groups of threadfin breams. All types of microorganisms in all groups of threadfin breams increased with statistical significance (p<0.05). When compared with the freshness quality criteria in terms of sensory, chemical, physical, freshness index and microbiology, it was found that all groups of threadfin breams were very fresh and suitable for raw consumption during the preservation and storage for 3 days. After 3 days of storage, the threadfin breams should be consumed cooked because the freshness quality of the fish is not suitable for raw consumption due to the increase in various parameters. The increase in various parameters is due to the deterioration of the fish and the activities of microorganisms. Therefore, threadfin breams is suitable to promote raw consumption within 3 days of storage. In addition, fish preservation, especially by Ikejime method, then cutting open the belly and storing in the refrigerator, can help improve the freshness of the fish. The results of this study can be used to develop techniques for preserving fish after capture for fishermen and can promote the increase in the value of threadfin breams in the future.

Read more
Directing for 3D Animation “The Red Mist”

คณะสถาปัตยกรรม ศิลปะและการออกแบบ

Directing for 3D Animation “The Red Mist”

The thesis artwork titled “The Red Mist” presents a narrative adapted from a short story of the same name by Assistant Professor Chatnarong Wisutkul in 2003. The story is set in a future world where people's greed and selfishness have led to a war, forcing them to rely on "breathing machines" to survive in the "red toxic mist." Phakin, a 15-year-old boy, embarks on a journey with a group of refugees. As they pass through abandoned cities, they encounter a boy without a breathing machine who has recently lost his father. Phakin decides to help him, despite objections from others. The boy tries to end his life by shutting off his breathing machine, and when Phakin intervenes to save him, he collapses from inhaling the toxic air. Witnessing Phakin's selfless act, the others are moved and join forces to save both of them. Phakin demonstrates that in difficult times, humans must cooperate and help each other rather than being divided and selfish.

Read more
The impact of climate change on the yield of Bambara groundnut in Thailand using the DSSAT model

คณะเทคโนโลยีการเกษตร

The impact of climate change on the yield of Bambara groundnut in Thailand using the DSSAT model

Climate change affects agricultural systems worldwide, including Thailand, and may lead to reduced crop yields, impacting food security. Bambara groundnut is a crop with the potential to adapt to changing environments and can thrive in areas with limited resources. This research aims to study the impact of climate change on Bambara groundnut yields in Thailand using the DSSAT (Decision Support System for Agrotechnology Transfer) model, an important tool for predicting plant growth under various environmental conditions. This study utilizes climate data, soil composition, and genetic information of Bambara groundnut to simulate and analyze yield trends under future climate scenarios. Four study areas in Thailand were selected: Songkhla, Lampang, Yasothon, and Saraburi. The CSM-CROPGRO-Bambara groundnut model was used to assess the impact of changing temperature and rainfall on the growth and yield of Bambara groundnut. The results of this study are expected to provide farmers and researchers with valuable information for planning cultivation and managing peanut production in response to climate change. Additionally, the findings can help formulate policy guidelines to promote the cultivation of climate-resilient crops and support the country's food security.

Read more