Abstract published in 1988-1995 to study the role

AbstractFrom the last few yearsartificial neural network is playing a very important role in businessanalytics and applications.  On studyingthe application of artificial neural network in the field of marketing andbusiness it revealed that most of the work is done on the financial distressand bankruptcy problems, stock price forecasting, and decision support, withspecial attention to classification tasks. Also the application of artificialneural network  in the marketsegmentation. In this ANN in segmentation is analyzed and the results of theclassification are reported; and finally, the conclusions, limitations andimplications of the study are discussed. IntroductionArtificial neuralnetwork are the computing systems based on the biological neural networks thatconstitutes the human brain.

It can be explain well with an example of imagerecognition, to recognize a cat they do it by using their prior knowledge aboutthe cats, i.e. they have furs, tails, whiskers, cat like face etc. Thecharacteristics of artificial neural networks such as efficiency, robustnessand adaptability make them a valuable tool for classification, decisionsupport, financial analysis or credit scoring made its utilization in variousfields for example scientific fields as well as in many business applications.Wong has reviewd the papers and articles published in 1988-1995 to study therole of artificial neural network in business.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

But he has seen that most of the  research was done in the bankruptcypredictions and stock forecasting. Later he also studied the work of it in thecollection of data and analyzing of these data. There are also various disciplines that have been studied includingaccounting, costs monitoring, customer analysis, finance, marketing or sales,manufacturing, process optimization, engineering or operational research havenot been included. In the second paper we have studied the application of ANNin segmentation.ResearchMethodologyTo study this we haveuse the keywords “literature review” “artificial neural network in marketing””business”,”finance”, “corporate”, “stocks”, “capital”, “costs”, “financial analysis”,”accounting”, “bankruptcy”, “exchange rates”, “financial distress”,”inflation”, “marketing”, “customers”, and “bonds”.It is essential to saythat maximum of the information gather from the articles were studied andutilized.In the secondpaper to study the application of ANN in segmentation Expert systems (ES) withapplication andInformation system are the most common approach. ApplicationareaNeural networkscaptures data by using itretive algorithms by comparing there synaptic weights.

But the main disadvantage was that it considers only the data with largeweights and do not consider data with small data because small data do notprovide significant result. Primarily due to unavailability of data researchersuse artificial data. Application of neural network in the field of business isvery significant because it is use to extract valuable information fromcomplex, nonlinear and noisy data. The applications of neural network inbusiness are as follows:·        Auditing and accounting·        Cost monitoring·        Credit scoring·        Customers metrics ·        Decision support·        Derivatives·        Exchange and interest rates·        Financial analysis·        Financial distress and bankruptcy·        Fraud analysis ·        Inflation ·        Marketing·         Sales·        Shares and bondsIn the secondpaper we have studied that in market segmentation methods can be largelyclassified based on two criteria for the four categories: a priori or post hoc,and descriptive or predictive statistical methods.When the type and number ofsegments are determined in advance by the researcher then the apriori approachis used and when the type and number of segments are determined based on theresults of data analyses then the post hoc approach is used. The post-hocmethods are relatively powerful and frequently used in practice . A single setof segmentation bases that has no distinction between dependent and independentvariables are related with the descriptive methods.

When one set consists ofdependent variables to be explained or predicted by a set of independentvariables then the predictive methods are applied.There are fourmajor classes of traditional algorithms for conducting traditional post hocsegmentation studies: Cluster analysis,Correspondence analysis, Searchprocedures, and Q-type factor analysis. Among clustering methods, the K-meansmethod is the most frequently used. An unsupervised neural network of theartificial neural networks (ANNs) where theoutcomes are nota priori have been recently applied to a wide variety of business areas.

TheKohonanSelf-Organizing Map of unsupervised ANN used in clustering for large andcomplexdata. Neural networksInthe application of neural networks in business almost all types of neuralnetworks are used. But there are cases in which uncertain work on neuralnetwork is done. So there is additional work should be done on these neuralnetwork so that we can get outcomes. Types of neural networkThemost popular neural networks used in the study was multilayer feedforwardneural networks in which neurons are organized into series of layers andinformation signal flows through the network solely in one direction, from theinput layer to the output layer.

Classification of frameworkClusteranalysis is a common tool for market segmentation. Conventional researchusually employs the multivariate analysis procedures. Comparison of threeclustering methods were done and proposed that SOM performs better clusteringthan the other conventional methods. A data mining associatiation ruile basedon SOM has been developed and applied to a sample of sales records fromdatabase for market fragmentation.

It was found that NN models outperforms themultinomial logut model in determining the most profitable time in a purchasinghistory to classify and target prospective consumers new to their categorie.deployed an ANN guided by genetic algorithms (GAs) successfully to targethouseholds. Targeting of customer segments withtailored   promotional activities is an importantaspect of customer relationship management. Application of  the SOM networks to a consumer data set theresearch established that the SOM network performs better than the two-stepprocedure that combines factor analysis and K-means cluster analysis inuncovering market segments.

All the selected articles were individually reviewedand categorized based on the proposed classification framework by the authorsof this paper. The proposed classification scheme is consisting of thefollowing phases:·        Onlinedatabase search·        Initialclassification by the researcher·        Verification of the classificationresultClassification of the articlesThefollowing 14 types of ANN algorithms are found to be applied on marketsegmentation research from the year 2000 to 2010 in the selected reviewed journals:i) NN algorithm, ii) Meta Heuristic tools, iii) ARNN(association reasoningneural network), iv) ART2 v) Bayesian NN, vi) Back Propagation NN, vii) DataMining, viii)hybrid fuzzy tools, ix) Genetic Algorithm(GA), x) hopefield NN,xi) hybrid NN, xii) SelfOrganizing Map(SOM), xiii) support vector machine(SVM), xiv) Vector Quantization. Learning algorithmTheprocess by which neural network updates its free parameters to capture thepatterns in the presented sample is called the learning. The most commonalgorithm used  in reviewing businessapplications was the backpropagation learning performed by gradient descentsearch.

This method is generally used because of its simplicity, universalityand good availability in softwares. Hybridization Thegroup of hybrid networks may be divided into two categories depending upon themethodology used: (a) dealing with learning process, (b) dealing with net-workarchitecture. The use of hybrid neural network is always having more importancethan ordinary neural networks. Benchmark methodByusing neural network method we can get better results rather than theconventional method. The most common benchmark methods identified in ourresearch are discriminant analysis , linear regression , logit and ARIMA. Thesignificant advantage of using conventional methods is their transperancy andcapability to comprehensibly interpret received results.

 CitationsNumberof citations contains information about which researcher is interested in.   Eventhough the probability of being cited depends on various factors suchaspublication time, journal accessibility, or field, citation count isanattractive measure for the evaluation of scientific performance. JournalThereview paper surveyed about a total number of 125 identified journals, firstsix journal have published 201 (53.

60%) papers and obtained 16,428 (58.71%)citations. Large number of involved journals indicates that the contribution ofneural networks is scattered across a wide range of different businessapplications.  Most of the journals revealed that most of theneural networks considered only real world application but not the underlyingfactors such as economic and financial theory.  ConclusionsInlast few decades artificial neural network has progressed very much.

It hasvarious applications in business fields but there were so much less papers werepublished in this field.  In our studywere financial distress and bankruptcy analysis, stock price prediction, andcredit scoring. It is interesting that the average number of financial analysisand derivatives articles stayed approximately the same throughout the examinedperiod.

On the other hand, research on shares, marketing, financial distress,and credit scoring has significantly increased compared to the early years ofour survey. After using neural networks in the business fields there were alsothe fields which were not investigated. This is true not only for thequalitative data but it also includes the quantative data just like cost, debtfinancing and bonds.Inhybridization secondary methods perform much better than the traditionalfeedforward networks trained by gradient based techniques. The specific hybridnetworks might work well only for particular tasks, our survey suggests thatproper integration of met heuristic methods into the neural network methodologymight be a key for achieving the optimal performance.Neuralnetworks have been successfully applied in wide range of business tasks andwere able to detect complex and nonlinear relationships without requiring anyspecific assumptions about the distribution or characteristics of the data.There is  lack of formal background andthe explanatory abilities are the two essential problems that have to beresolved to improve the neural network business studies.

The further researchtherefore should focus on universal guidelines and general methodology for thesetting of control variables, selection of hidden layers and overall design ofthe topology, since the quality of models reviewed in this study considerablydepended on experiences of the researchers. Moreover, robust measures thatcould assess the relevance of individual explanatory variables are verydesirable, since researchers are currently still careful with interpretation oftheir results and perform their validation using conventional methods. We areconvinced that research on artificial neural networks in business has stillmuch to offer. With their undisputed advantages, general availability of dataand increasing user-friendliness of soft-ware packages, neural networks willsurely attract more authors and offer additional possibilities forapplications.Applicationof artificial neural network techniques in market segmentation is an emerginginclination in the industry and academia. It has paying the attention ofresearchers, industry practitioners and academics.

This work has identifiedsixty four articles related to application of artificial neural networktechniques in market segmentation, and published between 2000 and 2010. Thisarticle aims to give a research review on the application of neural network inthe market segmentation domain and techniques which are most often used. Whilethis review work cannot claim to be exhaustive, but it presents reasonable insightsand shows the prevalence ofresearchon this area under discussion. ·        The majority of the reviewedarticles  34.

38% (22articles) and 21.88%(14 articles) are related common neural network algorithms.·        Thus a trend of ANN research tosegmentation is more obvious from the articles published in the kind of journalrelated to expert system development.

·        These articles could provide insight toorganization strategists on the familiar artificial neural network practicesused in market segmentation. ·        There are relatively fewer articles withthe metaheuristic, ART2, data mining, Genetic Algorithm and fuzzy algorithms.Despite the fewer number of articles related to the above category ofartificial neural network application to market segmentation, it does not meanthe application of artificial neural network in this aspect is less mature thanin the others. Applications of those algorithms in other domains, such asclustering or classification, may also be applied in segmentation if theypossess the same purpose of analysing the distinctiveness of customers/market.·        The k-means clustering model is the mostcommonly applied model in segmentation by partitioning a large market into thesmaller groups or the clusters of customers. ·        In order to maximize an organization’sprofits through segmentation, strategists have to both segment the market andthus increase the profitability of the organisation.

x

Hi!
I'm Mary!

Would you like to get a custom essay? How about receiving a customized one?

Check it out