Decision Support Systems In Banking Information Technology Essay

Introduction

1.0 Project background

The use of DM and DSS is becoming increasingly common. Many banks are upgrading from management instinctive decisions to mining of data and using it to make decisions for business growth, not only because of the bad result they get often from the instinctive decisions but from the fact that they need to mine the daily increase in data, look at the trends and patterns, and look for in accurate data to so as to make better decisions because of its wide support for business convenience and ease of use. “Data mining can be considered as a method that is used for a data warehouse which daily banks data are sourced for use and new once are stored, while DSS is a tool that helps develop and generate decisions based on the data mined. This includes the following characteristics:

A wide number of data is stored all over the banks departments and branches across its coverage and it accessed concurrently.

Heterogeneous execution environments composed of different hardware, network connections, operating systems, data formats, and data storage.

An extremely heterogeneous nature that depends on the large variety of data variables.

The ability of viewing customer data variables at run time according to user inputs and server status.

Most banks and financial institutions are adopting the combined technology of DM and DSS not only for cost effectiveness but also because it is more useful in supporting the day to day running of business activities in terms of speed, accessibility of customers business data, information dissemination and decision support.

Information sharing is important to any organization. Combined technology of DM and DSS, is however a major tool used by organization in making proactive decisions, on various product on offer for its customers and also customer retention.. It is a very good collaborative tool that provides employee (management staff) a convenient way of making well informed decision in a timely manner.

The use DM and DSS system is gradually increasing across the globe and eliminating the use of instinctive and predictive analysis by top management of banks within each department for its product and customers. The DM and DSS systems supports direct data transfer from one department to the other within the retail banking for analysis and decisions on customers account and also for marketing knowledge about the customer. It also provides for easy, fast, accurate and computerized business intelligence system.

1.1 Problem Statement

DM and DSS is such a challenging combined tool that requires high level of accuracy and professionalism. The risk involves inaccurate data, lack of data upgrade and instinctual decisions made by top management for heads of department with the banks. This could cost the bank a fortune ranging from reputational damage, legal sanctions, loss of customers confidence and huge financial loss to mention but a few.

Several challenges were identified as problems in improper use of data generated daily and its administration. But these challenges vary depending on the type systematic approach the bank is using. The following problems have been identified as challenges in delivering an effective DSS for banking as a tool.

Lack of performance Optimisation

Lack of competition with other sectors

Lack of informed decisions

Reduces profitability

Regulatory requirement

Informed online real-time

It is difficult to accurately make informed or draw relative good decisions due to the complexity and daily increase of data in banks. It has been an expensive practice when time consuming reservoir simulators are used. This has been the industrial standard approach. The solution depends on the development of simple and accurate model that will yield the same or close result to simulation using data mining methodology or technique(s).

However, collecting data will probably meet many problems, such as invalid data, redundancy, incomplete data etc. it will possibly lead to some incorrect results on decision-making. In this case, we will discuss some data mining methods in this project, in order to gain more correct and useful data

In the literature, knowledge discovery refers to the above multi step process while data mining is narrowly defined as the application of computational, statistical or visual methods. In practice, however, the application of any data mining method should be carried out following the above process and adopting CRISP-DM as it would be further explain in the Research Methodology section to ensure meaningful and useful findings. In this paper, ”data mining” and ”knowledge discovery” are used interchangeably, both referring to the overall knowledge discovery process.

1.1.2 Objective of Study

The major objective of this study is to develop some models that will relate and discover the following:

How DM and DSS work for retail banking.

Identifying areas where DM and DSS are utilized and can be utilized in retail banking.

Analyzing different patterns in the retail banking.

Identifying all business activities that require the application.

Demonstrate how business activities can utilize the application.

The impact of the DM and DSS in banking as a tool.

CHAPTER TWO

Literature Review

2.1 Introduction

Data mining is one of the most revolutionary developments of this decade. It defines data mining as a process of discovering meaningful new correlations by extracting and analyzing trends and patterns in large amounts of data stored in database or repositories, using pattern recognition technologies as well as mathematical and statistical techniques (Larose, 2005).

Groth (2000) also defines data mining as the process of finding trends and patterns in data, by sorting through large quantities of data and discovering new information.

“We are overwhelmed by information but ravenous of knowledge.” (Edelstein et.al 1997). It was observed that the problem today is not that there is not enough data and information streaming in. We are, in fact, flooded with data in most fields. Rather, the problem is that there are not enough trained personnel (human) who are available and skilled at translating all of this data into knowledge (Barquín et.al 1997).

Barquín (1997) further said, the ongoing remarkable growth of data mining and knowledge discoveries has been fuelled by a fortunate confluence of various factors such as: the explosive growth of data collection, storing of the data in data warehouses, availability of increased access to data from web navigation and intranets e.t.c References

However, data mining is not supposed to replace knowledge. On the contrary, it is supposed to be a tool to aid in the quantification of relative influences and reveal their inter-connectivity as well as giving insight into knowledge and decision making.

According to Edelstein et.al (1997), successful data mining depends on two key factors: developing a precise formulation for the problem to be solved and applying the right sets of data from its huge database. Edelstein et.al (1997), further stated that “The more the model builder can “play” with the data, build models, evaluate results, and work with the data some more (in a given unit of time), the better the resulting model will be. Consequently, the degree to which a data mining tool supports this interactive data exploration is more important than the algorithms it uses.”

2.2 Data Mining

Data mining is the task of discovering interesting patterns from large amount of data, where the data can be stored in databases, data warehouses, or other information repositories. It is a young interdisciplinary field, drawing from areas such as database systems, data warehousing, statistics, machine learning, data visualisation, information retrieval and high performance computing.

Database Technology

Statistics

Machine learning

Information science

Data Mining

Other Disciplines

Visualisation

Figure. 1. Data mining as a confluence of multiple disciplines

Source: (Han & Kamber, 2001)

2.2.1 Data Mining Concept

Data mining can be classified into two major categories; descriptive analysis which aims to characterize the general properties of data in the repositories, while predictive mining task predicts the characteristics and types of the unknown data based on its features.

This mining concept can further be stressed out under their classifications which are as follows:

Classification according to kinds of knowledge mined: Data mining system can be categorized according to the kinds of knowledge mined, that is based on data mining functionalities, which include characterization, classification, prediction, clustering, association and correlation analysis.

Data mining systems can also be categorized as those that mine data regularities i.e commonly occurring patterns versus those that mine data irregularities i.e. exceptions. In general, concept description, association and correlation analysis, classification, prediction and clustering mine data regularities.

Classification according to the kinds of techniques utilized: Data mining systems can be categorized according to the underlying data mining techniques employed. These techniques can be database oriented, machine learning, statistics, visualisation, pattern recognition, neural networks.

Classification according to the applications adapted: Data mining system can also be categorized according to the application they adapt. For instance, a data mining application may be tailored specifically for banking purpose which thereby creates different knowledge management within different departments as to how the data is mined. Therefore, a generic data mining system may not fit domain specific mining tasks.

2.2.2 Data Mining Framework

Enterprise modelling is considered as the process of building models of the whole or part of the enterprise such as process models, data models, resource models, etc., based on the knowledge about the enterprise, previous models and/or reference models as well as domain ontologies and model representation language (Vernadat, 1996). Then mining models are directed to logically fit or overlap with enterprise models, except that they are obtained by knowledge discovery (Shen et al. 2004).

Generally, these models describe the business process across the enterprise and the related modelling and integration framework enables a common understanding and analysis of the business activities. The models can be complemented and improved with mining descriptive models describing patterns in existing data about an enterprise’s behaviour and past performances. The mining predictive models could be used to forecast enterprise model evolution and its future business behaviour as position on the market. These models may evaluate the initial enterprise model, its evolution during model execution and its achievement and forecast future business (Neaga et al 2005).

Enterprise Knowledge could be classified as follows:

Knowledge about the past which is stable, voluminous and accurate

Knowledge about the present which is unstable, compact and maybe inaccurate.

Knowledge about the future which is hypothetical.

Knowledge management and data mining are critical process applied to existing enterprise database in order to find new information, knowledge and patterns which shows the future enterprise behaviour and improve its business performance (Neaga et al 2005).

Framework could also be defined as a conceptual methodology which shows how all the specific architectures that an organisation might define, can be integrated into a comprehensive and coherent environment for enterprise systems.

It is an analytical model or classification scheme that organises descriptive representations. It does not describe an implementation process and is independent of specific guide lines ( Frank et al. 2005).

In summary, this framework has the following characteristics (Zachman 1996).

Simplicity: It is easy to understand and it is not technical, but purely logical.

Comprehension: It addresses the enterprise as a whole. Any issues can be mapped against it to understand where they fit within the context of enterprise as a whole.

Language Supporting: It helps to think about complex concept and their communication precisely with few and non-technical terms.

Planning tool: It helps make better choices about the enterprise planning and its objectives. It is possible to find the best alternatives in the context of a complex business with a range of alternatives.

Problem-Solving: It enables working with abstractions, to simplify and to isolate simple variables without losing sense of complexity of the enterprise as a whole.

Neutrality: It is defined totally independently of tools or methodologies and therefore any tool or any methodology can be mapped within the framework.

Application to support customer relationship (CRM) supply chain management (SCM) and Enterprise resource Planning (ERP) no link !!!!

A Taxonomy of data mining task

Advances in Knowledge Discovery and Data Mining

Fayyad et.al 1996

Fayyad, G. Piatetsky-Shapiro, P. Smyth, R. Uthurusamy

ŽEds.., Advances in Knowledge Discovery and Data Mining,

MIT Press, Massachusetts, 1996, Chap. 1.

Where is the title!!!

M.J. Shaw et al. Decision Support Systems 31 (2001) p.127-137

Knowledge management Process

Sources: M.J. Shaw et al. Decision Support Systems 31 (2001)p. 127-137

2.2.3 Data Mining in Banking

The banking industry is continually recognizing the importance of the information it has on its customers. This industry has high information demands and uses information technology not only to improve the quality of service, but also to gain a competitive advantage (Hwang et al., 2002). The enormous amount of data that banks have been collecting over the years can greatly influence the success of data mining efforts.

According to Fabris (1998), by using data mining to analyze patterns and trends, bank executives can predict with increased accuracy how customers will react to adjustments in interest rates, which customers will be likely to accept new product offers, which customers will be at a higher risk for defaulting on a loan, and how to make each customer relationship more profitable. Data mining is proving itself very useful in the banking industry. In the following sections, examples are given of how the banking industry has been effectively utilizing data mining in the areas of:

Marketing,

Risk management,

Fraud detection, and

Customer acquisition and retention.

2.2.3.1 Marketing

One of the most widely used areas of data mining for the banking industry is in marketing. The bank’s marketing department uses data mining to analyze customer databases and develop statistically sound profiles of individual customer preferences for products and services. By offering only those products and services the customer really wants, the bank saves money on promotions and offerings that would otherwise be unprofitable (Decker, 1998). Bank of America uses database marketing to improve customer service and increase profits. By consolidating five years of customer history records, the bank is able to market and sell targeted services to their customers (Cabena et al., 1998). By revealing patterns of customer behaviour, their profitability can be determined and the bank can also expand its business by offering each individual customer other products and services.

2.2.3.2 Risk Management

Data mining is also used for risk management in the banking industry. Bank executives need to know whether the customers they are dealing with are reliable. Offering new customers credit cards, extending existing customers lines of credit, and approving loans can be risky decisions for banks if they do not know anything about their customers. Data mining can be used to reduce the risk of banks that issue credit cards by determining those customers who are likely to default on their accounts. An example given by Kuykendall (1999) is of a bank discovering that cardholders who withdrew money at casinos had higher rates of delinquency and bankruptcy. Crook et al. (2001) report that credit scoring was one of the earliest financial risk management tools developed. Credit scoring can be valuable to lenders in the banking industry when making lending decisions. Lenders would not have expanded the number of loans they give out without having an accurate, objective, and controllable risk assessment tool (Crook et al., 2001). The examples of both a good and a bad loan applicant’s histories

can be used to develop a profile for a good and bad new loan applicant (Cabena et al., 1998). Data mining can derive the credit behaviours of individual borrowers with installment, mortgage, and credit card loans, using characteristics such as credit history, length of employment, and length of residency (Decker, 1998). A score is produced that allows a lender to evaluate the customer and decide whether the person is a good candidate for a loan or if there is a high risk of default.

Fraud Detection

Another area where data mining is used in the banking industry is in fraud detection. Groth (1998) reports that, in banking, the most widespread use of data mining is in the area of fraud detection. Being able to detect fraudulent actions is an increasing concern for many businesses; and with the help of data mining, more fraudulent actions are being detected and stopped.

Data mining has been used extensively in the banking and financial markets. In the banking industry, data mining is heavily used to predict credit fraud, to evaluate risk, to perform trend analysis and to analyse profitability, as well as to help with direct marketing campaigns

In the financial markets, neural networks have been used in stocks-price forecasting in option trading, in bond rating, in portfolio management, in commodity price prediction, in mergers and acquisitions as well as in forecasting financial disasters.

The wide spread use of data mining in banks has not been unnoticed. In 1996, Bank Systems and Technology commented: “Data mining is the most important application in financial services in 1996” (Groth, 1998).

Delivering Predictive Technologies in a Real-Time Environment, the challenges is to take this knowledge and;

Deliver to customer-contact points

Put it in combination with business rules

Leverage information you may have gathered during customer interaction

Provide an immediate feedback loop on the effectiveness of an active marketing campaign

Allow marketers to fine-tune their campaigns on the fly.

2.3 Decision Support System

DSS is an interactive computer-based system which helps decision makers utilize data and models to solve unstructured problems (Gorry and Scott-Morton, 1971).

The term DSS can be used as umbrella term to describe any computerized system that supports decision making in an organization, where different departments such as marketing, finance, and accounting have different expert system. DSS encompasses all. (Gorry and Scott-Morton, 1978).

DSS is the area of information systems that is focused on supporting and improving top management decisions. (Arnott et al., 2005). Today computerized capabilities that can facilitate decision support in a number of ways, includes the following

Speedy communication: A computer allows enables the decision maker to perform many computations quickly and timely decisions on issues.

Improved communication and collaboration: Many decisions are made today by groups whose members maybe in different locations. Groups can collaborate and communicate readily using Web-based tools.

Improved data management

Managing giant data warehouses: Large data warehouses require special methods, to compute, organize and mine data.

Quality support: Computers can improve the quality of decisions made, for example, more data can be assessed, more alternatives can be evaluated, forecasts can be improved, risks analysis can be performed quickly, and views of experts as well

Anywhere, anytime support: Using wireless technology, managers can access information anytime and from anyplace, analyze and interpret it, and communicate with those involved.

2.3.1 Decision Support System Concept

Intelligence

Problem or opportunity

Environment, scanning reports, queries, and comparisons

Implementation

Design

Choice

Compare and select

Put solution into action

Creativity; find alternatives, and solutions

Figure 2: The Steps of Decision Support Gorry and Scott-Morton (1971)

Source: Decision support and business intelligence Systems

DSS can be described further into their type which includes:

STRUCTURED DECISIONS

Decisions can be categorized according to the degree of structure involved in the decision-making activity. Business analysts describe a structured decision as one in which all three components of a decision i.e. the data, process, and evaluation are determined (N.D. Gupta et.al 1989). Structured decisions are made on a regular basis in business environments, as it is expected in banking as a marketing tool for its business.

Structured decision support systems may simply use a form to ensure that all necessary data is collected and that the decision making process is not skewed by the absence of necessary data. When there is a desire to make a decision more structured, the support system for that decision is designed to ensure consistency. Many banks that hire individuals without a great deal of experience provide them with detailed guidelines on their decision making activities and support them by giving them little flexibility. Interestingly, consequence of making a decision more structured is that, the liability for inappropriate decisions is shifted from individual decision makers to the larger organization (N.D. Gupta et.al 1989).

SEMI-STRUCTURED DECISIONS

In the middle of the continuum are semi-structured decisions, and this is where most of what are considered to be true decision support systems are focused. Decisions of this type are characterized as having some agreement on the data, process, and/or evaluation to be used, but are also typified by efforts to retain some level of human judgement in the decision making process. An initial step in analyzing which support system is required is to understand where the limitations of the decision maker may be manifested (i.e., the data acquisition portion, the process component, or the evaluation of outcomes).

The two types of decisions i.e. unstructured and semi structured can be particularly problematic for small businesses, which often have limited technological or work force resources. According to Gupta et. al., (1989) “many decisions situations faced by executives in small business are one-of-a-kind, one-shot occurrences requiring specifically tailored solutions approaches without the benefit of any previously available rules or procedures. This unstructured or semi structured aggravates the problem of limited resources and staff expertise available to a small business executive to analyze important decisions appropriately. Faced with this difficulty, an executive in a small business must seek tools and techniques that do not demand too much of time and resources and are useful to make his life easier.” Subsequently, banks have increasingly turned to DSS to provide them with assistance in business guidance and management (Gupta et. al., 1989).

UNSTRUCTURED DECISIONS

At the other end of the field are unstructured decisions. While these decisions have the same components as structured ones, i.e. data, process, and evaluation, there is little agreement on their nature. With unstructured decisions, for example, each decision maker may use different data and processes to reach a conclusion. In addition, because of the nature of the decision there may only be a limited number of people within the organization that are even qualified to evaluate the decision (Gupta et.al 1989).

Unstructured decisions are made in instances in which all elements of the business environment, i.e. customer expectations, competitor response, customer retention, sales forecast, product marketing etc. are not completely understood (new product and marketing strategy decisions commonly fit into this category). Unstructured decision systems typically focus on the individual or team that will make the decision. These decision makers are usually entrusted with decisions that are unstructured because of their experience or expertise, and therefore it is their individual ability that is of value. One approach to support systems in this area is to construct a program that simulates the process used by a particular individual. In essence, these systems commonly referred to as “expert systems” prompt the user with a series of questions regarding a decision situation. “Once the expert system has sufficient information about the decision scenario, it uses an inference engine which draws upon a data base of expertise in this decision area to provide the manager with the best possible alternative for the problem,” (N.D. Gupta et.al 1989). According to Gupta et.al 1989 “The purported advantage of this decision aid is that it allows the manager the use of the collective knowledge of experts in this decision realm. Some of the current DSS applications have included long-range and strategic planning policy setting, new product planning, market planning, cash flow management, operational planning and budgeting, and portfolio management.”

Another approach is to monitor and document the process that was used so that the decision maker(s) can readily review what has already been examined and concluded. An even more novel approach used to support these decisions is to provide environments that are specially designed to give these decision makers an atmosphere that is supportive to their business requirement. The key to support of unstructured decisions is to understand the role that individuals experience or expertise plays in the decision and to allow for individual approaches.

2.3.2 Decision Support System Framework

DSS methodology recognises the need for data to solve problems. These sets of data can come from sources including the Web. Every problem that has to be solved and every opportunity or strategy to be analysed requires some data. Data are the first component of the DSS framework followed suit by uses of the data, which is for marketing and how it does imply before decisions are made through the DDS. Data related to a specific situation are manipulated by using models, which are the second component of the DSS framework which can be standard or customised. Some systems have a knowledge component which is the third component of the framework, where users are the fourth and vital component of the framework where the data is being transformed or mined into useful knowledge via the user interface.

Data

User Interface

Knowledge

Models

2.2.3 Decision Support System in Banks

Mathematical and analytical models are the major component of a Model-Driven DSS. Each Model-Drivel DSS has a specific set of purposes and hence different models are needed and used. Choosing appropriate models is a key design issue. Also, the software used for creating specific models needs to manage needed data and the user interface. In Model-Driven DSS the values of key variables or parameters are changed, often repeatedly, to reflect potential changes in supply, production, the economy, sales, marketing, costs and /or other environmental and internal factors. Information from the model is then analysed and evaluated by the decision-maker. Knowledge -Driven DSS use special models for processing rules or identifying relationships in data (Groth, 2000).

The DSS Architecture and networking design component refers to how hardware is organized, how software and data are distributed in the system, and how components of the system are integrated and connected. A major issue today is whether DSS should be available using a Web Browser on a company intranet and also available on the Global internet. Networking is the key driver of communications-Driven DSS.

Using Data Driven DSS and Knowledge driven DSS above for framework

Dominant DSS Component

Target User: Internal to External

Purpose: General to Specific

Deployment Technology

Data Driven DSS

Managers and Staffs

Query a Data Warehouse

Main Frame, Client/Server, Web

Knowledge Driven Database

Internal Users

Management Advice or Choose Product

Web/or Client Server

Source: http://dssresources.com/papers/supportingdm/sld019.htm

2.4 The Relationship between Data Mining, Decision Support System and marketing

The relationship between Data Mining and Decision Support System is important because they both complement each other’s work, they are stand alone technology but of benefits to each other. Data mining can be used to create patterns and help in Knowledge discovery within the data warehouse, but does not make decisions as it only draws data output for machine learning that is used in decision support system (M.J. Shaw et al. 2001). Not only can data mining improve decision making by searching for relationships and patterns from the extensive data collected by organizations, but it can also reduce information overload (Zhu et al., 2001). This highlighted relationship of DM and DSS also affects marketing in banking both positively and negatively because if data is not analysed properly it affects what is being decided or knowledge derived at the DSS phase of the complimentary standalone tools of both DM and DSS. The data analysed through the CRISP-DM methodology process is used as a decision support tool in marketing for banks, because banks receive enormous data in their data bank every minute of a working day and this data needs to be mined and used appropriately for the customers and also optimising performance across departments within the bank, which includes:

Credit Risk

Fraud detection

Customer retention

Product marketing

Knowledge Organization, distribution and refinement

Source: M.J. Shaw et al. Decision Support systems (2001)

The diagram in Figure 3 gives a description of how data is being stored and called out into different categories, the diagram explains three databases, which are: customer database, transaction database, and product database, this databases, classifies and categorises the data, checks for the customer characteristics and match it with a preference product based on the category of the customer, which also matches the customer through the product database with a preference product.

2.5 The Impact of Data Mining and Decision Support System on marketing

There is an increasing realization that effective customer relationship management ca