Text Mining and Predictive Analytics Applications in Banking and Higher Education
Overview
This paper examines two case studies demonstrating business intelligence applications: BBVA's use of text mining to enhance customer service and security, and APUS's implementation of predictive analytics for student retention. The analysis illustrates how organizations across different sectors leverage data mining, text analytics, and machine learning to drive operational improvements and data-driven decision-making.
What this coursework covers
- BBVA case study: text mining applications for customer service automation, language translation, chat summarization, and fraud detection
- APUS case study: challenges of online education, data sources utilized, and predictive analytics for student dropout prevention
- Implementation of decision management systems and text analytics as tools for business intelligence deployment
Preview
Chapter 7
BBVA utilized text mining to improve its customer service. The text mining tools were used to process comments and messages that were received through various channels and make the information actionable. The company uses data mining with analytics to enhance customer service within the organization. Text mining can also be used in marketing and enhances customer relationships. When used effectively, text mining can enhance sales through effective customer relationship management. Through text mining and analytics, an automated system was created that was able to respond to queries and convert text to speech. BBVA could also use text mining to translate foreign languages as well as summarize chats with customers for future reference. Text mining can also be a means to enhance the security of the banking system by installing a detection system that analyses whether a statement is true or deceptive (Sharda, Delen, & Turban, 2015).
Chapter 8
APUS faced numerous challenges because it was a new online organization. They faced stiff competition from the non-online institutions as well as its web-based competitors. Because it was new, it was difficult to break-even in the market and earn a large customer share. Many clients doubted whether they should choose APUS because it was relatively new. The main types of data that APUS tapped included demographic data, registration data, course-level data. The main obstacles faced included utilizing data sourced from diverse domains and sources, processing of natural languages using text analytics, as well as massive information for effective and appropriate data mining.