How is data mining applied to decision making?

Introduction

Data mining is not actually a new concept to man it is as old as man’s existence. It is just that the name it has, and the method of data acquisition was crude in practice to man over the years. As man shifted from the use of crude tools and a traditional means of data acquisition, to the advent of technological devices. This had made it possible for the creation of Data mining tools and softwares in order to get the required data from an existing databank, mart or warehouse.

The subject matter Data mining is a very important tool that has helped in further creating new ideas and right decision making in business organization, government and also in the advancement of technology. And a review of how data mining is applied to decision making is an important focus of this research work.

Order custom essay How is data mining applied to decision making? with free plagiarism report

450+ experts on 30 subjects Starting from 3 hours delivery

Get Essay Help

Historical Background Of Data Mining

The foundation of today’s data mining techniques can be traced or dated back to the 1950’s when the work of mathematicians, logicians, and computer scientists combined to create artificial intelligence and machine learning(Buchanan,2006).

During the 60’s Artificial Intelligence and statistics practitioners created new algorithms like regression analysis, maximum likelihood estimates,neural networks,liner models of classification and bias reduction(Dunham,2003:p.13).

Throughout the 1970’s,1980’s and 1990’s the confluence of disciplines(Artificial Intelligence,Information Retrieval,Statistics,and Database Systems) with the availability of fast micro computers opened up a new world for retrieving and analyzing data.(Dunham,2003:Ibid)

In the 90’s the term Knowledge Discovery in Databases(KDD) had been coined with the first workshop held(Fayyad,Piatetsky-Shapiro and Smyth, 1996:p.40).This huge data volume as postulated by Fayyad et al gave rise to the need for new technique for handling massive quantities of information ,many of which was located in huge databases. Also in the 90’s the concept database warehouses,a term used to describe a large database alongside came Online analytical processing(OLAP) and association rule algorithms(Han.J. et al,2001:p.3).

Finally data mining became part of standard business practice.Business began using data mining to help manage all areas of the customer life cycle,including acquiring new customers,retaining good customers,increasing revenue from existing customers(Two Crows,1999:p.5).

Definition Of Terms

Information: This is described as a processed fact and this information got from data is analysed from a large existing data makes it possible for decision to be made rightly following the gathered important information.

Data processes: Data which is handled formally in any business or organization may undergo rigid,complex processing due to the required information that is to be derived for organizations use. Due to the rigid,complex processing nature it still can be broken down into simple steps. These steps are :

1. Classification
2. Sorting and rearranging of data
3. Summarizing/aggregating data
4. Performing calculations on data
5. Selection of data.

Decisions: Information got is what is transmuted to decisions. Decisions are taken by decision takers who have certain organizational objectives in mind with a certain way of processing and appreciating information. That is why the right information has to be supplied to decision takers in an organization.

According to(Kilman and Mitroff,1976),they regard individuals as falling into one of two categories in the way that they absorb information. Some people take in information best if it highly detailed and specific. The various elements of information need not to be linked as a whole.The other group absorbs information in a holistic way, that is in a less concrete way, preferring general facts, and softdata linked as a whole.

They further postulated that the group that absorbs the information in totality will be involved in a high degree of analytic thought in providing adequate and detailed justifications involving quantitative reasons in support of final decisions. While the other group will rely more on intuition,experience,rules of thumb and judgement making it difficult for this group to provide justification for recommended decisions.(Ibid).

Data Mining

It is important to understand what Data mining is, not only from a single perspective but from a broad one. This will entail looking at various scholastic definitions that expounds data mining as a subject.

Hand(1998) Opined that data mining is the process of secondary analysis of large databases aimed at finding unsuspected relationships which are of interest or value to the database owners. Hand’s definition is questioned in the area of database owners who owners database. Is it or should it be collective or individualisticThese questions should have been discussed in Hand’s definition.

Weiss And Indurkhya,(1998) Opined that Data mining is the search for valuable information in large volumes of data. This definition does not state the importance of data mining. The definition should include the importance or the relevance of the information to the individual, group or organization.

Haskett(2000) narrows his definition of data mining as set of techniques used in an automated approach to exhaustively explore and surface complex relationships in every large datasets.

Hand(Ibid) further postulated that data mining and statistical analysis are different from each other. In statistics he said data is collected with predefined set of questions in mind. Again according to Witten et al(2005:p.xxiii) Data mining refers to the process of finding interesting patterns in the data that are not explicitly part of the data. The idea from the scholastic definitions is that data mining can be defined as the extraction of the required data from a large volume of data (Data warehouse) which is to be analysed using data mining tools or techniques to provide the right information for an individual or a group of individuals in business organisations or institutions so that their decisions taken based on their futuristic predictions might become a positive reality.

Data mining can be on the following data:

1. Relational database
2. Data warehouses
3. Transactional databases
4. Political database e.t.c

Data Mining Techniques

According to Thearling(2002) the most widely used techniques in data mining are:

1. Decision Trees: This he described as a tree-shaped structures that rules for the classification of a data set. Examples of a decision tree methods are Chisquare Automatic Interaction Detection(CHAID) and Classification And Regression Trees(CART).
2. Rule Induction: The extraction of useful if-then rules from data based or statistical significance.
3. Genetic Algorithms: He explained this to mean optimization techniques that use processes such as genetic combination, mutation, and natural selection in a design based on the concepts of evolution.
4. Artificial Neural Networks: Non-linear predictive models that learn through training and resemble biological neural networks in structure.

Business Intelligence

Business intelligence can be defined as the intelligence got from an available data bank using data mining tools or techniques to further aid decision making after analysis. Furthermore business intelligence can also be referred to as computer based techniques used in identifying and extracting important business data and analysing the data, such as sales or by associated costs and income(Business Dictionary,2010).

With the right business intelligence the right decisions are made to bring about organizational achievements, or profit maximization. Having the right business from data analysis using data mining technique or tools can help to create new ideas in business or any co-operation that seeks to introduce new products or improve on existing products that would be of important benefit to the user or consumer.

Tools And Techniques For Generating Business Intelligence

There are a number of tools and techniques for generating business intelligence. These include:

1. Document management system
2. Decision support system
3. Digital dashboards
4. Data mining
5. Group decision support
6. Data warehousing
7. Online analytical processing(OLAP)

Important Features Of Business Intelligence

Organizational structure is based on one important reason to meet up organization’s aims and objectives. And for this reason having the right business intelligence and its tool application holds the key to organizational achievement. It is then very paramount to discuss some of these important features of business intelligence.

Improved Business Strategy Support: The objectives and aims of any business is based upon right and accurate information. With the right and accurate information on ground there can be an improved business strategy.
Gaining Competitive Advantage: An organization’s deep understanding about environment, self and competitors can make use of the intelligence got to gain competitive advantage.
Structured And Unstructured :This entails how data is retrieved. It can be got from other or outer sources not only from the formal or structured outputs of business transactions.

Data Mining And Its Impact On Business

The impact of data mining on business is explained by Simbarashe Chikonyora. Simbarashe Chikonyora (2011) opined that Data mining which is the process of taking large amount of information and analysing it from a variety of angles and putting into a format that makes it a useful information to help a business improve operations, reduce costs, boost revenue ,and make better business decisions, with the help of effective data mining soft wares. He further explained that data mining is mostly used by business with a strong emphasis on consumer information such as shopping habits, financial analysis, marketing assessments….etc which allows a business to determine key factors such as product ,positioning, competition, customer satisfaction, sales and business expenditures. The result according to him is that business is able to streamline its operations, develop effective marketing plans and generate sales with an impact resulting to an increase in revenue and increase in revenue and increased profitability.

A Review Of How Data Mining Is Applied To Decision Making: Selected Case Study References

Jennifer Paddock et al (2011) took a study of about 65 companies and discovered that the mean return on a business intelligence investment, was over 400% over 2.5 years. Why was this and what could have been the resultThe following few case studies according to Jennifer pointed out the importance of Data mining as applied to decision making.

Seibel: A leading company supplier of front line office system offers an entirely web –based architecture provides enterprise –wide support for internal sales, marketing, and customer service organisations and extends that support throughout the entire enterprise, uniting third-party resellers and service providers, business partners, and customers into a single information system.

Chase Case Study: According to the case study by Jennifer. Chase decided to use Seibel’s front office solution as the cornerstone of its effort to unite customer relationship activities across department boundaries. Chase Manhattan is already experiencing increased communication and availability of information that enables the bank to treat its customers like people, not like account numbers. This suggests that Chase’s organization had a problem of adequate data information in relating with customers. The use of Seibel’s web-based architecture was the was last resort in solving the problem enabling all personnel in the organization to be able to work and access information in an integrated systemic order which had improved better customer relations, uniting third-party resellers and service providers, and business partners.

1. Boise Incorporated: This corporation had major challenges which was based on three main components:
2. Asset availability
3. Asset operating rate
4. The ability of the asset to produce a quality product.

But the data that was needed to measure the above components came from a variety of different system of different locations. This was taken care of when Monty Bryant, maintenance service manager at Boise Inc said “right out of the box”. Corda centre view dash boards software was able to receive data from all over different systems, aggregate data, normalize it and present it in the graphical formats that was needed(Corda,2011). Further more the Boise case study was able to itemize the following:

1. Save 520 man-hours annually through the automation of data collection and reporting process.
2. Avoid 150,000 dollars a year in infrastructure and resource costs.
3. Improve decisions by making business intelligence more accessible and visible
4. Respond to performance issue faster with less energy and less resource time.
5. Increase overall manufacturing productivity by at least 5% through asset and resource.

Problems Or Challenges Of Data Mining

Data mining applications makes use of database to supply the raw data for input.This can also pose as a challenge and the challenges according to(Kamelsh Mhashilkar,2011) are:

Uncertainty: This refers to the error and degree of noise in the data.Data has got to be precise for consideration in a discovery system
Databases usually has the challenge of noise. Noise is defined as errors in either the values or attributes or class. According to(Kamelsh 2011:Ibid) missing data can be treated by discovery systems in a number of ways such as:
Simply disregard missing values.
Infer missing values from known values
Omit the corresponding records.

Limitation To The Study

This research work limitation was the accessibility to important topical data relevant to the subject under review,due to bureaucratic bottleneck. But the available resources used for this research solved the problem.

Conclusion

Data mining tools or techniques have brought about a change in business. Decisions in any organization or business can not be based on experience alone, now in this day and age of wide range information and competition. The further development of data mining tools and software has also made it possible for private business owners to predictively forecast making the right decisions by maximizing profits. Data mining techniques is applied on or used by various sectors which is a blessing. Though data mining has got its challenges but one can say that data mining tools and techniques would only be improved upon based on futuristic challenges that might occur due to data complications.

References

1. Bunchanan,B.G(2006) Brief History Of Artificial Intelligence.Retrieved March 22,2006 From http://www.aaai.org/AITopics/b bhist.html
2. Business Dictionary(2010) Definition Of Business Intelligence,Retrieved 17 March 2010:www.business dictionary.com
3. Corda (2011) The Boise Case Study:From www.corda.com
4. Dunham,M.H (2003) Data mining Introductory And Advanced Topics:Upper Saddle River,NJ: Pearson Education,Inc
5. Fayyad,U.M et al(1996,Fall) From Data Mining To Knowledge Discovery In Databases.AI Magazine,17(3),pp.37-54
6. Hand.D.J(1998) Data Mining: Statistics And MoreThe American Statistician.2. 112-118
7. Han,J.And Kamber,M(2001) Data Mining:Concepts And Techniques(Morgan-Kaufman series Of Data Management System).SanDiego:Academic Press
8. Haskett Mitch(2000) An Introduction To Data Mining.Part 1.Understanding The Critical Data Relationship In The Corporate Data Warehouse.Enterprise System Journal.V.15:32-34
9. Kilman R.H And Mitroff.I.I(1976) Quantitative Versus Qualitative Analysis For Management Science:Different Forms For Different Psychological Types.Tims Interfaces,Februrary.
10. Simbarashe,C.(2011) Data Mining: From http://www.courses.co.za/users/admin
11. Thearling,K.(2002) “Data Mining Techniques”:Retrieved From http://www.3 shore.net/zkut/text/dmwhite/dm white.htm
12. Two crows(1999) About Data Mining(Third Edition).Retrieved February 7,2006 From http://www.two crows.com/about.dm.htm
13. Weiss.S.H And Indurkhya.N(1998) Predictive Data Mining:A practical Guide:Morgan Kaufman Publishers San Francisco CA.
14. Witten,I.H et al(2005) Data Mining:Practical Machine Learning Tools And Techniques(2nd ed,Morgan-Kaufman Series Of Data Management Systems)San Francisco:Elsevier.

Don't let plagiarism ruin your grade

Run a free check or have your essay done for you

Check my essay Hire Writer