Applications of BI Analytics and Data Mining

INTRODUCTION

The world of information and technology changes within a blink of eyes. There are no business organizations that are unaware of this rapid changing autonomous technology. The information age has changed dramatically over the past 20years where large quantities of data need to be handled. For these, the importance of data analytics continues to grow where companies are finding more and more applications for Data Mining and Business Intelligence. The motivation behind data mining can be taken from the famous saying of Aristotle- “The key is to know something that nobody else knows”. Data mining is a collective term used to describe different analysis techniques such as statistics, artificial intelligence and machine learning that are employed to scan huge amounts of data found in the organization’s databases or online databases. It can be defined as the exploration and analysis of large quantities of data in order to discover meaningful patterns and rules which help to make crucial business decision. For example; group together similar documents returned by search engine according to their context like Amazon rainforecast, Amazon.com etc. For extraction, data are generated through different sources such as social media, websites, transactions, mobile devices, sensors, etc. The main objective of this automated process is to extract valuable information from existing data that derive mission-critical business processes in order to gain competitive advantages and help business grows. The implication of data mining can be seen either in a banking sector or a health industry. The most prominent area of business focusing on Customer Relationship Management (CRM) is benefitted by data mining. Clinical decision making, Customer sales forecast, fraud detection, inventory management are some of the areas in which BI& data mining technique are contributing.

Applications of Data Mining

 Data Mining on Customer Relationship Management (CRM)

Customer relationship management (CRM) comprises a set of processes and enabling systems supporting a business strategy to build long term, profitable relationships with specific customers. It is a single enterprise view of the customer. It includes the process such as Sales Force Automation, Marketing Automation, and Customer Service. CRM helps to identify products, services and their relationship in order to manage and synchronize business communication and information. Data mining tools are a popular means of analyzing customer data within the analytical CRM framework that covers the predictive analytics of business analytics. Many organizations have collected and stored a wealth of data about their current customers, potential customers, suppliers and business partners. However, the inability to discover valuable information hidden in the data prevents the organizations from transforming these data into valuable and useful knowledge. Data mining tools could help these organizations to discover the hidden knowledge in the enormous amount of data. With comprehensive customer data, data mining technology can provide business intelligence to generate new opportunities.

Get Help With Your Essay
If you need assistance with writing your essay, our professional essay writing service is here to help!
Essay Writing Service

The implication of data mining technique in CRM is a developing pattern in the worldwide economy. Identifying and understanding client practices and attributes is the establishment of the improvement of a focused CRM methodology, in order to obtain and hold potential clients and expand customer value. Suitable data mining tools, which are good at extracting and identifying useful information and knowledge from enormous customer databases, are a standout amongst the best supporting devices for settling on various CRM choices. Data Mining in CRM helps to select the right prospects from a large list of potential customers, help companies offer the most appealing array of products to existing customers and identify customers where the company is at risk of losing. There are numerous machine learning techniques available for each type of data mining model. Choices of data mining techniques should be based on the data characteristics and business requirements. The results of using data mining in CRM is the improved profitability by optimizing customer interaction through the entire customer life cycle and reduced costs due to properly allocating of resources.

Illustration of Application

The famous illustration of how data mining improves the CRM process can be explained through the growth of online business. Among such e-business, one of the largest internet retailer in the world as measured by revenue and market capitalization is Amazon. There is no doubt Amazon’s revenue is increasing day by day and so is the number of its sellers. With over 5 million marketplace sellers across all Amazon marketplaces, it stands tall as one of the biggest markets for sellers. Amazon is shredding the competition due to the accurate and streamlined shopping journey it provided. Its success is attributed by their dynamic CRM system where they invested valuable time and money to build in-house software according to their needs.

Amazon and the Power of CRM are characterized by;

•          User friendly

•          Great selection

•          Convenience

Amazon gather information through customers searching and browsing which helps to tailor marketing campaigns and email campaigns based on things user will probably like. Amazon is one of many examples of how a good CRM solution can transform your business and ensure the success of your brand.

Challenges of Data Mining

Challenges of Business analytics and Data Mining on CRM

•          to collect a CRM data for the research

•          results almost always need a combination of different algorithms

•          In CRM data came from different sources, so this need a strong integration before the analysis of these data

•          Privacy and confidentiality considerations for data and analysis results

•          Developing deeper models of customer behavior

Data Mining on Banking Sector

The banking industry has lots of data related with finance, customer details, property valuation document, credit document and many more. Such information may be confidential and need to keep safe for the future decision making action. As a result, the bank operates the data mining to store the data in a systematic way and a protective way. The flow of data in bank is excess and to control data mining technique is used as a means to overcome the problem.

According to Ramageri and Desai, 2013; Moradi et al., 2013; Moin and Ahmed, 2012; Hammawa, 2011, there are various parts in which data mining can be operates in monetary parts like client division and profitability, credit examination, foreseeing instalment default, marketing, fake exchanges, positioning investments, optimizing stock portfolios, money the executives and anticipating activities, most beneficial Credit Card Customers and Cross Selling. Some of the application of business analytics and data mining that are using on banking sector are mentioned.

Customer Relationship Management

Today clients have wide scope of items and services given by various banks. So that, banks need to cook the requirements of the client by giving such items and administrations which they like. This will result loyalty and retention of customer. Data mining software analyze the customer loyalty. IT looks the behavior such as customer is shifting from his bank to another, reasons for such shifting and the last transaction performed before shifting can be known which will help the banks to perform better and retain its customers

Marketing

The bank’s marketing department can use data mining to analyses customer databases. Data mining carry various analyses on collected data to determine the consumer behavior with reference to product, price and distribution channel. The response of the clients for the current and new items can likewise be known dependent on which banks will attempt to advance the item, improve nature of items and administration and gain advantage.

Risk Management

Bank officials need to know whether the clients they are managing are solid or not. Offering new clients MasterCard, expanding existing clients’ credit extensions, and endorsing advances can be dangerous choices for banks in the event that they know nothing about their clients. Banks provides loan to the customer by looking the various details relating to the loan such as amount of loan, lending rate, repayment period, type of property mortgaged, demography, and income and credit history of the borrower.

Fraud Detection

There is one system that has been successfully in detecting fraud i.e. Falcon‟s „fraud assessment system‟Radivojevic, Z., Cvetanovic, M., & and Milutinovic, V. (2004). This is used by the top ten credit card issuing banks. The data mining techniques helps the organization to focus on the available resources of dissecting the client information all together to recognize the examples that hat can lead to frauds.

Opportunities of Business analytics and Data mining on banking sector

A huge amount of data gets in the banking sectors as it becomes great for anybody involves ingathering useful information. Expanding innovation and future application regions dependably makes new difficulties and opportunities PASCU, A. I. (2018). Advance information mining strategies can be created and utilized by R& D and other data rich organizations to find valuable examples that can help in research or business advancement to guarantee the development and advancement of the organizations. Some of the opportunities are as follow.

Micro-marketing campaigns will explore new niches.

Advertising will target potential customers with new precision.

Prediction of behaviors and trends

Discovery of previous unknown patterns

Using large set of parallel computers

Challenges of Business analytics and Data mining on banking sector

Some of the Challenges faced by banking sector of having business analytics and data mining are given below.

1.1.  Privacy Concern

In recent years, with the boom in using internet, the privacy concern has been increasing. Due to privacy concern, Bankers are apprehensive that obscure individual may approach their own data and afterward utilize that data in an untrustworthy manner and this may make hurt them.

1.2.  Security Issues

Another biggest challenge is security issue which is a major concern on banking sector. Banks has a lot of personal information about the about the employees and customers including social security number, with finance, customer details, property valuation document, credit document and it is also available in online (Radivojevic, Cvetanovic, & and Milutinovic, 2004).. But, they don’t have adequate security frameworks set up to secure this data. They have been a great deal of situations where hacker access and stole individual information of clients.

1.3.  Misuse of Information/Inaccurate information

Propose obtain from data mining intended to be used for banking ethical purpose (Chitra, 2013). However, it may misuse for other unethical purpose. Unethical organizations or Individual may utilize the data to exploit of defenseless individuals or to oppress a specific gathering of individuals. Aside from that, information mining systems is not penny percent precise one. In this manner oversights may happen which can have genuine outcome.

Data Mining on HealthCare Industry

As the importance of data analytics continues to grow, companies are finding more and more applications for Data Mining and Business Intelligence. Among all application and industries, Healthcare industry is one of the long suffered from limited resources, ever increasing demand, and questionable value if we insight into the past performance of the health care system. Which tells why change was necessary? Because a need of change, Healthcare organizations are swimming in an ever-deeper pool of data. As per Eckerson, (2003) stated, without a planned program to target data, gather, deliver and analyze the most relevant data, these organizations will continue to be data rich but information poor. So forward thinking, it is very important to present the role of Business Intelligence technology in the healthcare sector improve patient and service outcomes. In order to achieve the full benefits of BI and data mining technique in healthcare organizations, there must be a strategic approach to tactical projects and realize that the greatest efficiencies result from historically integrated data into operational and clinical systems (Microsoft, 2009).

Bi and data mining technique can use sophisticated algorithms to ‘ learn ‘ features from a large volume of data on health care, and then use the insights obtained to assist clinical practice. It can also be equipped with learning and self-correcting skills to enhance feedback-based accuracy.In addition, an AI system extracts useful information from a large population of patients to help make real-time health risk alert inferences and predict health outcomes. Prior to deployment of BI tool in healthcare industry, They need to be ‘ trained ‘ by data generated from clinical activities such as screening, diagnosis, treatment assignment, and so on, so that similar groups of subjects, associations between subject features and interesting outcomes can be learned. During deployment, a substantial proportion of the AI literature analyzes data from diagnostic imaging, genetic testing, and electro diagnosis at the diagnostic stage. For example, when analyzing diagnostic images containing vast data information, Jha and Topol urged radiologists to adopt AI technologies. Li et al addressed that the use of abnormal genetic expression in long non-coding RNAs to diagnose gastric cancer.

To analyses the clinical laboratory results, different data sources which are summarized in table 1 are distinguished with pattern matching, genetic and electrophysiological data. This process is called data generation. The reason of doing this is that data sources contain the large portion of unstructured data which are bit difficult to analyze. As a consequences, Bi application focus on converting the unstructured data to machine-understandable electronic medical report.

Table.1

Example data sources within a healthcare delivery system

Data Source

Data Generated

Electronic Health Record (EHR)

Clinical documentation, patient history, results reporting, and patient orders.

Laboratory Information System (LIMS)

Laboratory results (the LIMS is typically interfaced with the EHR)

Diagnostic or monitoring instruments

Range from images (e.g., magnetic resonance imaging) to numbers (e.g., vital signs) to text report (result interpretation). May or may not be interfaced with the EHR.

Insurance claims / billing

Information on what was done to the patient during a visit, the cost of those services and the expected payment. The level of service is often determined from data in the EHR.

Pharmacy

Information on the fulfillment of medication orders. Not typically part of the EHR.

Human resources and supply chain

Lists of employees and their roles in the institution; location and utilization of medical supplies. Not typically interfaced with the EHR.

Real-time locating systems

Positions and interactions of assets and people

In addition, data extraction is use of standard terminology and key element of analytical process to increase the interoperability and exchange of Electronic Health Record (EHR) data. This is explicit measures to enable patients to view, download, and transmit (VDT) their results. This is an attempt to put patients more in control of their health and their health data. 

Furthermore, Analysis depends on the context in which it is conducted. Clinical care and improvement of performance may require very different perspectives of data and may use data in unique ways. In the last process of analytics, advanced visualization and reporting techniques can provide more consistent, clean and unambiguous charts that can enhance user decision-making speed and reliability

Much BI application plays a vital role in death causing disease likewise Stroke that affects more than 500 million people worldwide. Research on stroke prevention and treatment is therefore of great importance. Early detection and diagnose were implemented into the device for the model building solution. Machine learning treatment has also been applied for predicting and analyzing the performance of stroke treatment. Outcome prediction and prognosis evaluation methods have advantages in improving prediction performance.

The evolving IT platforms also present BI and DW techniques with visualization tools that put actionable insights into caregivers and patients ‘ hands, allowing providers to invent new healthcare practices as necessary. The advantages of this approach are: better preventive care; IT simplification; and better, more personalized treatment. BI technology emerges as a positive impact on Health care organization. The need of this technology in health economy only focusing on patients outcomes. Nowadays, patients can be treated either from health sector or from home. All this is happening because of the introduction of BI and DW techniques.

Fig. 1.Patients Taking Charge of Health Choices

To sum up, the time has come for the healthcare sector to change. Using analytics will enable people with the potential to generate lifesaving or lifestyle-enhancing insights to put the right data at the fingertips. BI and DW provide breakthrough opportunities for new research and discovery, improved patient care, and increased health and health care efficiency.

References

Han, X. X., Lei, J. H., Zhao, X. X., Luo, P., & Li, J. F. (2014). Application of Data Mining in CRM. Applied Mechanics and Materials, 444, 1776-1780. doi:10.4028/www.scientific.net/AMM.444-445.1776

Data, S.  Retrieved from https://www.suntecdata.com/blog/4-killer-strategies-to-successfully-market-your-amazon-listing/

Ramageri, B.M. and B.L. Desai, 2013 Role of data mining in retail sector. Int. J. Comput. Sci. Eng., 5

Balan, V. J. (2013). A REVIEW ON DATA MINING IN BANKING SECTOR. American Journal of Applied Sciences, 1160-1165.

Chitra, D. K. (2013). Data Mining Techniques and its Applications in Banking Sector. Exploring Research and innovation, 219-226.

Kazi Imran Moin, D. Q. (2012). Use of Data Mining in Banking. International Journal of Engineering Research and, 738-742.

PASCU, A. I. (2018). DATA MINING. CONCEPTS AND . Economy Series.

Radivojevic, Z., Cvetanovic, M., & and Milutinovic, V. (2004). Data Mining: A Brief Overview. Plurix, Germany.: Electrical Engineering.

M. L. Ivan, M. Velicanu, I. Taranu.(2015). Using Business Intelligence in Healthcare System. The 14th International Conference on Informatics in Economy, 2284- 7472.

Ward, M. J., Marsolo, K. A., &Froehle, C. M. (2014). Applications of Business Analytics in Healthcare. Business horizons, 57(5), 571–582. doi:10.1016/j.bushor.2014.06.003