Application of AI in customer relationship management

Application of AI in customer relationship management

• 1.
  Application of AIin Customer Relationship Management:A systematic review By - Shashwat Shankar (IMB2018017)
• 2.
  Introduction 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 (Ling & Yen, 2001). the rapid growth of the Internet and its associated technologies has greatly increased the opportunities for marketing and has transformed the way relationships between companies and their customers are managed (Ngai, 2005). CRM is as an “enterprise approach to understanding and influencing customer behaviour through meaningful communications in order to improve customer acquisition, customer retention, customer loyalty, and customer profitability”. The importance of viewing CRM Is a comprehensive process of acquiring and retaining customers, with the help of business intelligence, to maximize the customer value to the organization.
• 3.
  Contd. From the architecturepoint of view, the CRM framework can be classified into operational and analytical (Berson et al., 2000, He et al., 2004, Teo et al., 2006). Operational CRM refers to the automation of business processes, whereas analytical CRM refers to the analysis of customer characteristics and behaviours so as to support the organization’s customer management strategies. As such, analytical CRM could help an organization to better discriminate and more effectively allocate resources to the most profitable group of customers.
• 4.
  Classification method Classification methodAccording to Swift (2001, p. 12), Parvatiyar and Sheth (2001, p.5) and Kracklauer, Mills, and Seifert (2004, p. 4), CRM consists of four dimensions: ● Customer Identification; ● Customer Attraction; ● Customer Retention; ● Customer Development. The generative aspect of data mining consists of the building of a model from data (Carrier & Povel, 2003). Each data mining technique can perform one or more of the following types of data modelling: ● Association; ● Classification; ● Clustering; ● Forecasting; ● Regression; ● Sequence discovery; ● Visualization.
• 5.
  Classification framework for AI techniques in CRM
• 6.
  Classification framework –CRM dimensions ● Customer identification:- To properly identify target markets, it is necessary to perform thorough market research on the volume of products and services sold and used over a broad demographic area. ● Customer attraction:- Customer Attraction Marketing makes it easy for customers to understand your product and assess its value through legitimate means. Attraction marketing improves engagement. The key to success when using attraction marketing lies in having a genuine interest in customers and their needs.
• 7.
  Contd.. ● Customer retention:-The customer retention is the process of engaging existing customers to continue buying products or services from your business.The best customer retention tactics enable you to form lasting relationships with consumers who will become loyal to your brand. ● Customer development:- Customer Development is basically a simple methodology and a process for getting out of the building and talking to potential customers, the market — before building anything.
• 8.
  Stages of customerdevelopment The four steps of the framework are: 1. Customer discovery – Understand customers and their needs that you may be able to satisfy. 2. Customer validation – You have a product that will satisfy your customer’s needs. 3. Company creation – You determine whether your product will satisfy all the customers needs 4. Company building – You can grow your organization in order to support the demand for your product.
• 9.
  Classification framework –models ● Association Association aims to establishing relationships between items which exist together in a given record (Ahmed, 2004, Jiao et al., 2006, Mitra et al., 2002). Market basket analysis and cross selling programs are typical examples for which association modelling is usually adopted. Common tools for association modelling are statistics and apriori algorithms. ● Classification Classification is one of the most common learning models in data mining (Ahmed, 2004, Berry and Linoff, 2004, Carrier and Povel, 2003). It aims at building a model to predict future customer behaviours through classifying database records into a number of predefined classes based on certain criteria (Ahmed, 2004, Berson et al., 2000, Chen et al., 2003, Mitra et al., 2002). Common tools used for classification are neural networks, decision trees and if-then-else rules.
• 10.
  Contd... ● Clustering Clustering isthe task of segmenting a heterogeneous population into a number of more homogenous clusters (Ahmed, 2004, Berry and Linoff, 2004, Carrier and Povel, 2003, Mitra et al., 2002). It is different to classification in that clusters are unknown at the time the algorithm starts. In other words, there are no predefined clusters. Common tools for clustering include neural networks and discrimination analysis.
• 11.
  Contd... ● Forecasting Forecasting estimatesthe future value based on a record’s patterns. It deals with continuously valued outcomes (Ahmed, 2004, Berry and Linoff, 2004). It relates to modelling and the logical relationships of the model at some time in the future. Demand forecast is a typical example of a forecasting model. Common tools for forecasting include neural networks and survival analysis.
• 12.
  Contd.. ● Regression Regression isa kind of statistical estimation technique used to map each data object to a real value provide prediction value (Carrier and Povel, 2003, Mitra et al., 2002). Uses of regression include curve fitting, prediction (including forecasting), modeling of causal relationships, and testing scientific hypotheses about relationships between variables. Common tools for regression include linear regression and logistic regression.
• 13.
  Contd... ● Visualization Visualization refersto the presentation of data so that users can view complex patterns (Shaw et al., 2001). It is used in conjunction with other data mining models to provide a clearer understanding of the discovered patterns or relationships (Turban et al., 2007).
• 14.
  Problem Statement 1. Thereis not any comprehensive and systematic study about reviewing and analyzing the important techniques for CRM and AI application. 2. There is a discrepancy in CRM if the use of AI can make it more effective or not. 3. Despite the importance of data mining techniques to customer relationship management (CRM), if there is a competitive advantage when the company uses AI.
• 15.
  Method Web of Science,Science Direct, Emerald Insight, and Google Scholar databases were carefully searched in between June 2019 for the articles published in the English Language in their journals, to find the suitable articles that were available until June 2019.
• 16.
  Lorem ipsum dolorsit amet, consectetur adipiscing elit. Curabitur eleifend a diam quis suscipit. Fusce venenatis nunc ut lectus convallis, sit amet egestas mi rutrum. Maecenas molestie ultricies euismod. Morbi a rutrum nisl. Vestibulum laoreet enim id sem fermentum, sed aliquam arcu dictum. Donec ultrices diam sagittis nibh pellentesque eleifend. Data Source Search Syntaxes Web of Science TS=(customer relationship management* near/1 intel*) OR TS=(customer service* near/1 management*) AND TS=(artificial intelligence) OR TS=(ai) OR TS=(artificial intelligence) OR TS=(dyad*) Science Direct ("customer relationship management" OR "customer service management") AND ("artificial intelligence" OR "ai" OR "artificial-intelligence") Emerald Insight ("customer relationship management" OR "customer service management") AND ("artificial intelligence" OR "ai" OR "artificial-intelligence") Google Scholar ("customer relationship management" OR "customer service management") AND ("artificial intelligence" OR "ai" OR "artificial-intelligence") -machine learning -eCRM -"artificial intelligence"
• 17.
  PRISMA FLOW DIAGRAM
• 19.
  Distribution of articles byCRM and AI model
• 20.
  Classification of thearticles Moreover, the distribution of the articles by year of publication is shown in Fig. It is obvious that publications which are related to CRM,customer service management, data mining in CRM, data quality in CRM, have increased significantly from 2009 to June 2015. In 2010, the amount of publication decreased approximately 70% when compared with 2008
• 21.
  Distribution of articles byAI techniques
• 22.
  References W. H., &Chan, K. C. C. (2003). Mining fuzzy association rules in a bank-account database. IEEE Transactions on Fuzzy Systems, 11, 238–248. Au, W. H., Chan, K. C. C., & Yao, X. (2003). A novel evolutionary data mining algorithm with applications to churn prediction. IEEE Transactions on Evolutionary Computation, 7, 532–545. Bae, S. M., Ha, S. H., & Park, S. C. (2005). A web-based system for analyzing the voices of call center customers in the service industry. Expert Systems with Applications, 28, 29–41. Bae, S. M., Park, S. C., & Ha, S. H. (2003). Fuzzy web ad selector based on web usage mining. IEEE Intelligent Systems, 62–69. Baesens, B., Verstraeten, G., Dirk, V. D. P., Michael, E. P., Kenhove, V. K., & Vanthienen, J. (2004). Bayesian network classifiers for identifying the slope of the customer-lifecycle of long-life customers. European Journal of Operational Research, 156, 508–523. Baesens, B., Viaene, S., Poel, D. V. D., Vanthienen, J., & Dedene, G. (2002). Bayesian neural network learning for repeat purchase modelling in direct marketing. European Journal of Operational Research, 138, 191–211
• 23.
  Thank you!