Consumer analytics toward development of cross selling products at retail banking an approach on big data at eximbank

TO PHUC NGUYEN KHUONGCONSUMER ANALYTICS TOWARD DEVELOPMENT OF CROSS SELLING PRODUCTS AT RETAIL BANKING: AN APPROACH ON BIG DATA AT EXIMBANK MASTER THESIS Ho Chi Minh City – 2020... TO P

TO PHUC NGUYEN KHUONG

CONSUMER ANALYTICS TOWARD DEVELOPMENT OF CROSS SELLING PRODUCTS AT RETAIL BANKING:

AN APPROACH ON BIG DATA AT EXIMBANK

MASTER THESIS

Ho Chi Minh City – 2020

TO PHUC NGUYEN KHUONG

CONSUMER ANALYTICS TOWARD DEVELOPMENT OF CROSS SELLING PRODUCTS AT RETAIL BANKING:

AN APPROACH ON BIG DATA AT EXIMBANK

Specialization: Business Administration

Executive Business Administration

TUTOR: ASSOC.PROF DR TU VAN BINH

Ho Chi Minh City - 2020

I would like to assure you that all of the help for the implementation of this dissertation was thanked and the information cited in the thesis has been traced.

Trainees implement the thesis(Sign and write full name)

Decision, and Association Analysis are applied The findings show thatconsumers’ characteristics using services at EXIMBANK are various, in which staffs, directors as individual customers occupy a high proportion in total customers Based on descriptive statistics, there are eight main products, such as

VG (Visa Gold), VC (Visa Classis), MG (Master Gold), MS (Master Standard),

VP (Visa Platinum), VV (Viva Violet Card), VA (Visa Auto Card), and others are concerned most by the customer, in which VG and VC are the two top cards used Directors are more interested in VG card, while staffs concern VC card In addition, using two cards, called the main card and the extra card, is popular This

is a potential chance for the bank to develop cross-selling products, which the product bundle strategies are packed into groups Based on the method Association Analysis, propobality of using two cards or three cards at the same time of customers are derived This finding basically supports the bank to addresscross-selling products of cards to customers To do this, recommendations of the strategies of bundle products are suggested in the thesis, together with implementation plans

TABLE OF CONTENTS

LIST OF FIGURES

LIST OF TABLES

CHAPTER 1: INTRODUCTION 1

I RATIONALE OF RESEARCH 1

II OBJECTIVES OF STUDY 2

III RESEARCH QUESTIONS 2

IV SCOPE AND LIMITATION 3

V RESEARCH METHODOLOGY 3

Data collection 3

Methods to analyze data 5

CHAPTER 2: CONCEPTS CONCERNED AND ITS FRAMEWORK 7

I CONCEPTUAL FRAMEWORK 7

Service retention 7

Remaining good relationships between the customer and retail banking 8

1.The concept of big data and its consideration in banking 8

2 Big data in Banking and its contribution 9

Application of Big Data to investigate the customer’s spending habits 10

Customer segmentation and review customer’s records 10

The sales includes other services (service cross-selling) 11

Building a system to record customer feedback 11

Personalized marketing 12

Flexible suggesting good services to customers 12

3 Customer lifetime value based on RFM 16

4 Customer segmentation 18

5 Cross-selling products 19

CHAPTER 3: BIG DATA OF BANKING INDUSTRY AND CONCEPTS APPROACHED………21

I SITUATION OF EXIMBANK AND ITS BUSINESS 21

II BIG DATA AND ITS APPLICATION IN BANKING 25

III DATA ANALYTICS 29

1.PROFILE OF CUSTOMER 29

2.RMF AND MARKET SEGMENT 33

Cross – Selling strategy 38

Summary of chapter 43

CHAPTER 4: CONCLUSION AND SOLUTIONS 44

I GENERAL CONCLUSION 44

II FINDING OF MARKET SEGMENTS 44

III DETAILED CHARACTERISTICS BY MARKET SEGMENT 45

IV IDEAS OF MARKETING STRATEGY 46

V SOLUTIONS 46

1 PRODUCT STRATEGY 46

2 PRICE STRATEGY 48

3 PROMOTION STRATEGY 49

4 PROCESS STRATEGY 50

VI EMPLICATION OF STATEGY 48

REFERENCE

Web link:

APPENDIX

Figure 2.2: Customer value matrix and its description 16

Figure 2.3: The diagram of proposed model 18

Figure 3.1: Share of investment in big data analytics by sector 26

Figure 3.2: Share of investment in big data analytics by sector 26

Figure 3.3: Position of customer 29

Figure 3.4: Type of products that consumers concerned 30

Figure 3.5: Length of service of active customers 31

Figure 3.6: Type of customers using services at the bank 32

Figure 3.7: Type of products that consumers concerned 33

Figure 3.8: Matrix of LOS and Recency 34

Figure 3.9: Market segments based on RFM 36

Figure 3.10: Result of Tree Decision of five market segments 38

Figure 3.11: Result of Association Analysis and its potential bundles 39

Figure 3.12: Characteristics of potential bundle product between MS and VA 40

Figure 3.13: Potential bundle strategy (MS-VA) by customer income 41

Figure 3.14: Characteristics of potential bundle product among VP, MS, and VA 41

Figure 3.15: Potential bundle strategy (VP-MS-VA) by customer’s income 42

Figure 3.16: Characteristics of potential bundle product among MG, VV, and VA 43

Figure 3.17: Potential bundle strategy (MG-VV-VA) by customer’s income 43

Figure 4.1: Ranges of account balance of customers 45

Figure 4.2: Marketing strategies suggested to the bank 46

LIST OF TABLES

CHAPTER 1: INTRODUCTION

I RATIONALE OF RESEARCH

Rapid development of information technology in the banking industry has created a big concern that the banks must think of how to explore internal data to serve competitive strategies In fact, currently, most banking institutions, insurances and financial services are attempts to adopt a new approach toward data mining to the development and innovation of services that they provide to customers Like most other industries, big data analytics are going to be a major change to support business units to generate campaigns for a short term and long term strategies to attract more new customers, retain existing ones and fight against the competitors

Investing a big data system cause simulation that data mining is much concerned in the banking industry, because it supports to extract valuable information form huge amounts

of data Particularly it contributes into finding out consumer behavior and present a market situation picture of a firm However, it is not easy to explore big data of firms Data scientists developed quantitative methods as mathematic approaches, such as descriptive and predictive analytics, etc

Nowadays, banks have realized the importance of customer relation, this is one of successful factors However, challenges of how to retain most profitable customers and

to reduce a churn rate are problematic To solve this problem, consumer behavior should

be investigated and analyzed, which big data are a worth resource and quite helpful to measure and predict consumer behavior correctly Therefore, the power of data is to derive utility across various spheres of their functioning, product across selling, regulatory compliance management, risk management, and customer service management

As we know, particularities of banks’ activities generate a huge amount of data from unstructured data, such as transaction history, customer to the unstructured data such as the customer’s activities on the website, or the mobile banking application on social networks However, how to explore big data available is the most problem Although there are not few banks who recognize that and want to turn the big data available to the most effective weapon for the market competition, they are seemly facing problems of new system, skills, and so on

With changes in integration policies of Vietnam through information technology system, together with fire competition, more and more banks in Vietnam have paid more attention to investing a huge money for big data system and people capacity For example, EXIMBAK is one of the banks, who is willing to pay money to structure data

system very early It realizes benefits of data warehouse to support business strategies

In fact, the benefits of internal brought not the raise of the internal management efficiency, but also help increase the competitive advantages, maximize profits

Currently, the banks must be flexible for their plan toward activities of innovation, in term of capturing needs of customers and improving satisfaction and retention of customer By the way, CRM is quite helpful and recognized for acquisition and retention

of customers As a result, the bank can get more opportunism to make long lasting and profitable relationships with customers

To investigating big data system of the bank, Eximbank has offered a program of building capacity for staffs, who are directly related to data analytics and business development In addition, the department of database is established to exploit internal database, which the role of an employee is placed in the ecosystem talent development However, everything is seemly concerned and exploited more and more toward data mining, predictive analytics on customer behavior

II OBJECTIVES OF STUDY

- Presenting characteristics of consumers who are using services of banking

- Analyzing history of transaction behavior of consumers

- Identifying and developing market segments through consumer behavior

- Developing developments of cross-selling products to increase benefits of customers toward customer retain

III RESEARCH QUESTIONS

There are some questions concerned as follows

(1) What are characteristics of consumer toward service usage at banking?

(2) How do customers take transaction at the bank?

(3) How is the market segment developed?

(4) What are cross-selling product developments to increase benefits of customers

to retain them?

IV SCOPE AND LIMITATION

The thesis only concerns on internal database as well as big data of Eximbank located in

a district of Ho Chi Minh City Due to the confidential information and secret information requirements, the name of district is asked to hidden Even the study is not taken qualitative method into the study, because the author is the head/leader of the branch of Eximbank, what the thesis is done it is based on actual demand of the bank Its finding is actual expectation for the Eximbank’s business plan in the time coming

V RESEARCH METHODOLOGY

Data collection

Data used are extracted from data warehouse of the bank Because of security requested, this thesis is seriously asked to be confidential Using information as well as findings of this study is not convinced, it must be responsible for who going to use that

Data pre-processing is taken into account of the data mining process, because it improves the accuracy and efficiency of subsequent modeling (Han & Kamber, 2006) Activities

of data pre-processing techniques are data cleaning, data transformation, data integration and data reduction, these are concerned, due to data quality

The database used in the study is extracted from data warehouse of the bank, which the period of study is 12 months, from January 1, 2019 to December 31, 2019 Accordingly, the database selected has 130,000 rows, equivalent to 3,527 customers This means one individual customer has more transactions during study, so the rows are more than the customer amount As presented in table 1.1, 25 fields or variables are taken into account

of the current study Each one has a defined measurement, such as nominal, continuous, date, categorical

Table 1.1: Information of variables concerned

4 Type of customer Type of customer

+ Credit customer + Individual customer + family business customer

Nominal variable

7 Document score Score on initial documents of customer

+ Prestige + Good enough + Unknown

Nominal

+ Manager + Worker + Director + Office staff

Nominal

14 House ownership Status of house property of customers

+ Owned house

Nominal

+ Rented house + Stayed with parents’ house

+ only loan services from Eximbank + loan services from Eximbank > another bank

+ loan services from Eximbank = another bank

+ loan services from Eximbank < another bank

+ No loan services from Eximbank

Nominal

19 Balance account Balance account measured in Vietnamese

Methods to analyze data

Data mining is one of tools concerned toward descriptive statistics In addition, clustering techniques is employed to cluster customers into groups, which it to satisfy two main criteria: (i) each group or cluster is homogeneous; (ii) each group or cluster should be different from other clusters This method mainly gains customer

segmentation In term of classification method, the cluster of K-means is employed to segment customers (Khajvand & Tarokh, 2011)

Input variables recruited in the cluster method are generated by the RFM indicator, which

R as Recency, F as Frequency, M as Monetary are generated Since segmentation is on the basis of Recency – Frequency – Monetary (RFM), the selected features of data to meet RFM is included last transaction date (purchased), count transaction (purchase) and total monetary that customer took loan during one year and count item which refers

to variety of customer taken transaction To count transaction, it is the frequency of customer transactions In data transformation, the data is transformed in a way that can

be exploited by data mining tools

C&R Tree as “Classification and Regression Tree” is also employed to investigate customer behavior in more detailed It is supported to develop classification systems toward prediction based on a set of decision rules Application of this method known as rule induction brings several advantages Based on this the marketer can think and develop campaigns to retain customers and stimulate their consumption

Association Rules as the method of Association Analysis, it presents an association based on antecedent and consequent It means that once the antecedent is true, then the consequent is also true Association rules present a probabilistic rule and modify probability of consequent happened exactly, given that the probability of “antecedent”

is truly happened

Suppose there are two inputs of X and Y employed in the method Results of Association Analysis give indicators, which the confidence and the lift are concerned in this study The confidence is defined as the conditional probability to find in a group Y having found X, while the lift presents whether the association between X and Y is positive or not With lift ≥ 1 it gives a message of positive association between X and Y, otherwise negative association is happened

CHAPTER 2: CONCEPTS CONCERNED AND ITS FRAMEWORK

I CONCEPTUAL FRAMEWORK

Service retention

Retaining current customers and returning them to loyalty has played an important role

to save and reduce business cost To obtain this, currently banks have used a variety of advanced analytical tools to find out customer behavior and grow customer relationships for maximizing profitability Because of the competitive market, most commercial banks pay more attention to analytics on database available that determine habits of top performers, rather than what drive customers, and looking forward to application of big data in spheres like front office risk management to back office trade operations Some

of them calls over in-person meetings to investigate necessary information

In addition, to retain the customers, banks are wise to investigate a broad spectrum of data and measure data points across multiple segments of clients Once data are deeply explored, the company can get higher efficiency with a low cost In fact, many types of costs can be accursed in the business unit, e.g costs of advertising to entice new customers, costs of a personal selling pitch to new prospects, costs of communication to explain business procedure for new clients and dealing These costs can be reduced if the business units have a good approach on data mining For example, banks in Vietnam have a high investment on big data system to record customer behavior from different channels

Loyalty in retail banking: Customer loyalty is one of criteria that any company is concerned very much However, still some bankers have a little agreement among them

to what behaviors constitute customer loyalty and how best to stimulate these behaviors However it is not easy to earn loyalty, because of fierce competition This is reason the most bankers want to be typically of product-oriented programs Still many retail bankers are not clear of thinking of the customer loyalty with two distinct, e.g customer stratification and customer retention As the following, classification of these two definitions are presented

Customer satisfaction: what the customer is expecting, she or he is fulfilled, which his

or his needs, wishes or desires on products or services are met However, it is not convinced to be sure guarantee of retention or loyalty (Szus & Tóth, 2008) Srivastava

& Gopalkrishnan (2015) used big data in Indian banks to analyze the customer satisfaction measurement Accordingly findings showed poor services and other issues

that customers complain Based on that marketing strategies are suggested to Indian banks

Customer retention: Unlike customer satisfaction and customer loyalty, customer retention is an ability to remain customer over time and measures a relationship between the customer and the firm Once customer is retained longer, expectation of loyalty is possible (Jaiswal, et al., 2018) However, according to Kumar, et al (2013), indicating customer satisfaction offers only small portion of variance in loyalty, but not convince much to enhance customer retentions

Retail banks are often guilty of mistaking customer inertia for loyalty Correct cognition

on customers can be on the four quadrants of behavior-attitude scale (Truly Loyal, Accessible, Trapped, Higher Risk), also must be awareness of the differences between the behaviors that customers display their attitudes toward the bank Once the customer

is trapped, but not loyalty, they can be remained for a long term But this customer can leave any time once it realizes the bank in low esteem As a result, to understand the degree of loyalty gaps, the bankers need to know very well the characteristics of customers as consumption behavior and how to connect between satisfaction and retention As argued by Szus & Tóth (2008), it is not easy to know that customer loyalty can be possible to be displayed as customer retention

Remaining good relationships between the customer and retail banking

Because of fire competition, retail banks have paid more attention to revamping loyalty programs toward customer This is strongly considered toward incorporating a reward system into the bank’s plans Currently, many retail banks offer a significant number of potential rewards to promote and solidify customer loyalty The banks develop a relationship based on two-way street, which the customer will remain relationship only once there is value in doing so However, once the customers’ purchase volume is increased and beneficial relationship gradually takes shape, the customers’ relationship with banks is remained (Jaiswal, et al., 2018)

1 The concept of big data and its consideration in banking

There are many studies using big data to analyze customer consumption (Khajvand & Tarokh, 2011), these studies mention that big data as the tool allow a business unit to manipulate, create and manage huge data sets, also it is stored and required to support the volume of data, characterized by variety, volume and velocity1

Big data can be both structure and unstructured with the large volume of data It records activities designed in the system If doing business, this data is recorded consumption

history of customers during period, it is enriched on a business a second-to second or day-to-day basis by time It will change our world completely and is not a passing fad will a way It is what organizations can use to investigate on business issues, management issues or/and other sectors

Banks internationally are beginning to harness the power of data in order to derive utility across various spheres of their functioning, ranging from sentiment analysis, product cross selling, regulatory compliances management, reputational risk management, financial crime management and much more (Srivastava & Gopalkrishnan, 2015) Big Data play an important role to extract the data value and support to obtain better decisions Then, the high cost of running time, which will make the problem difficult to solve, can be avoided Through these techniques, financial companies will have less risk when predicting that customers will be successful in their payments So more people can get access to credit loans

2 Big data in Banking and its contribution

Once the number of customer increases, this affects to a certain extent, the bank need to think of providing quality Practice shows that the analysis of existing data has simplified the process of monitoring and assessing customers' credit banks and financial institutions, based on large volumes of data such as information, dossiers personal and other confidential information But with the big data available, banks can exploit to continuously monitor the behavior of the customer in real time, identify sources of data required to collect service of offering solutions Justice Evaluation process customer records in real time will gradually boost operational efficiency and profitability, thereby promoting further organizational development

According to Forbes, 87% of companies consider Big Data will create major changes to their industry until the end of the 2nd decade of the 21st century Even the company also think that without consideration on big data analytics and specific strategies based on empirical analysis will effectively make them fall in its business

There are many sources of Big data in most sectors and in different areas, not just in the banking sector and financial services Every interaction, every transaction of customers

at banks create electronic records, the backups are saved according to legal regulations, and transactions in the office ATMs in different locations as well information stored in the bank Thanks to analyze Big Data, companies financial services no longer store the data as required mandatory as in the past but now they are active, more active in the extraction to get the results that are based on that offer solutions to improve operations, increase the profitability of the organization

In short, Big Data is an important resource, its nature core creates competitive advantage

in any one financial institution does especially when capturing the needs of consumers increasingly complex though was more convenient, easier thanks to the boom of

technology and engineering Big data will not only bring the new look, the creation of the innovation process for each type of service to the customers but also ensure business efficiency, risk and cost are minimized

Identifying array of services, parts, functions within financial institutions, where Big Data can be reviewed for the purpose exploited most efficiently based on a combination

of knowledge, business model and the ability to apply software technologies to create competitive opportunities for the organization Depending on the purpose, structure, resources, capabilities vary from organization that will be more cases big data applications ranging nature special, separately Here are the use cases are the most popular - are we research and selection - which banks and companies financial services are performed to identify the value hidden deep inside the analysis of Big data

Application of Big Data to investigate the customer’s spending habits

The bank has the ability to directly access information resources, abundant historical data related to the habits and behaviors of customer spending The bank also holds information on the amount a customer is paid how much for example specific salary per month, the amount to be transferred into a savings account, the money was paid to the company provide utilities (e.g electricity companies, companies providing internet services, ), while customers using banking services, etc This provides a basis, opportunities for banks access and deeper data analytics Applying the information screening function (filter function), for example as the filter time or holiday celebrations and macroeconomic conditions (e.g inflation, unemployment, ), the reasons for bank employees can understand the cause of the impact as customer wage increases or decreases and spending capacity of customers change how This is one of the fundamental elements for the process of risk assessment, screening, evaluation profile lenders, evaluate the possibility of mortgage and offer financial products other (cross-selling) to customers as insurance

Banks benefit a lot if they know the information customers to withdraw cash - all the money has been on payday - or if they want to keep the money on a credit card (credit card) / debit (debit card) Take advantage of that, banks can reach customers, expand service with the proposal, to attract customers to invest in short-term loans with high payout ratio and the appropriate interest rate, etc

Customer segmentation and review customer’s records

Once the initial analytics of the spending habits of customers with identifying the type

of service, channel transactions are priority customers (i.e customers who want savings

or want to invest in loans), the will get a database serving the segment and classify customers as appropriate based on the information and documents supplied by clients Customers who spend comfortable ease, investors cautious yet thorough,

customers pay the debts quickly, customers began to repay the maturing, Big Data will give banks the knowledge, expertise and deep habits spending patterns of customers, simplifying the task of identifying the needs and wants of them By being able to track each transaction by customers, the bank’s will be able to classify customers based on various parameters, including services often customers use, time to use the service, spending habits when using a credit card or even a net asset value (net worth - income plus the value of customer assets minus liabilities)

Benefits that bring customer segmentation is that it allows banks to target customers with better marketing campaigns relevant is designed to meet the exact needs of the customer Data analysis capabilities for Big Data rising companies and organizations BFSI grasp the need to find hidden within each customer (customer insights) thereby creating customer segments However, the collection and evaluation of information the requirements are investment in the infrastructure of the organization as well as investment in affiliate network between all employees of departments, functional parts

of the organization technology, advanced engineering software for the process of exploiting Big Data

The sales include other services (service cross-selling)

Based on a database which banks can attract or retain customers by introducing more other services For example, banks can introduce investments with attractive interest rates to customers who have idle money or investors’ always careful consideration in making investment decisions Or the bank has proposed short-term loans to customers who have a habit of spending "comfortable" for the needs of their daily consumption or customers who are having difficulty in paying old debts Analyzing correctly on the profile of the customer, the bank can cross-sell other services more efficient and attract more customers with better deals to be "personalized" to focus precisely on demand customer demand more efficiently, thereby increasing revenue for the company

Building a system to record customer feedback

Customers can leave feedback after every transaction or every time to get advice from the customer call center or via the feedback form, but often to share ideas through social media, e.g Facebook, Zalo Big Data tools can search for sifting through the information and feedback publicly on the social media and collect all the data mentioned

on the brand of the bank to be able to respond quickly and fully to customers Also supports prevent rumors affecting business operations and customer confidence in banks, this was already happened in some Vietnamese banks currently

Once customers think that the bank is willing listen to them and appreciate their comments as ideas related to service improvements, the bank can create more chances

to retain its customers To do this better, the banks should build a data center - storage

centers all the interactions customers have with brands including private data base, transaction history, browsing history, services, etc with the purposes are to support campaign developments to meet what the customers are expecting to increase their loyalty

Personalized marketing

As previously mentioned, the application of Big Data analytics into business strategy of bank plays an important role to identify needs of each customer based on its comments, feedback In addition, consumption behavior is significantly explored through transaction history As a result, if the consumption information is clarified, it is quite well to support the bank in direction of personalized marketing to individual customers Once customer segmentation is concerned by big data, banks can take advantages to personalized marketing to target customers based on understanding of personal spending habits of them In addition, to obtain good database on the transaction history of customers, the banking needs to combine data unstructured - a form of data Big Data - obtained from social networking or social media such as customer profile on Facebook

To get a more complete picture of the needs of customers based on the analysis of the psychological desire at all times point On the other hand, the data of the customer in the background social media or social applications other smart will help banks analyze the risks that may occur, but consider whether to provide loans or outside the evaluation of dossiers as usual

After analyzing and understanding the specific needs and particular of each customer, the bank should continue to segment even further and provide solutions, marketing plans accordingly to thereby obtain response rate recovery, higher conversion rate from each customer For example, banks use the e-mail marketing to be sent to customers the latest information about the services for short-term loans with interest rates moderate, or deposits with attractive interest rates, or chapters the other privileges, the creation of products and services provided to each customer segment, or even each specific client will help banks build brand image and build a good relationship in each client

Flexible suggesting good services to customers

System Big Data can be a complex system linking various parts different functions, but its job is to simplify the tasks of an organization officials Whenever a customer name

or account number is entered into the system, the system of Big Data will support screening all data and transmissions or provide the data required to serve the process analysis This will enable banks to optimize workflow and save both time and costs Big Data will also allow the organization to identify and fix problems before they affect their customers

Big Data is only given as a result, information such as which customers are likely not repay the debt, or the customer has the ability to leave the service (churn risk) and duties

of each bank is thinking a solution to fix the example monitored "closely" and continuous information on the repayment period to customers who have the habit of delay in the payment of interest As a result, Big Data is right to bring positive solutions, e.g customer segments, service improvements, and campaigns to retain existing customers and attract new ones

II CONCEPTS RELATED TO APPROACHED QUANTITATIVE

METHODS

1 RFM

As known, RFM is a good tool to measure customer behavior, it seems as an incredible and perceived technique to evaluate the customers’ commitment to business units and differentiates important customers from large data by three attributes of recency, frequency and monetary Based on customers’ purchasing history, RFM is quite supported to address customers’ classification and ranking

According to (Cheng & Chen, 2009), the detail definitions of Recency, Frequency and Monetary method are described as the following: (i) Recency (R) is defined as an interval between the time when the latest purchasing order presents and happens such as one week, one month or one quarter A lower recency value means that customers frequently visit to company Likewise, the higher value implies that in the near future, customer sometimes or rarely visits the company; (ii) Frequency (F) is shown as the number of purchasing transactions made in a given period of time by customer, for example, one time per year, two times per quarter or three times per month The higher frequency value, the more loyal customers regarding company; (iii) Monetary (M) is identified as total money amount that customers spent during one specified time So, the much more money amount of consumption, the more earnings customers bring to the company Accordingly, (Wu & Lin, 2005) demonstrated that the higher the value of R and F is, the more comparable customers make a new transaction with companies In addition, the higher M value is, the more comparable customers purchase products or services of companies in several times

All customers are analyzed by recency, frequency, and monetary scores which take place

in the scale from 1 to 5 as a quintile based on its original records, in which1 being unlikely and 5 being likely Scores of combination of RFM are assumed to get remarkable attributes as shown in table 2.1 Once all R, F and M are the most recent, the most frequent, and the highest spend, respectively, the score of customers belong to this group is called “champions” with the highest score of 5 Conversely, once indicators of

R, F, M are the least recent, only one transaction, and the lowest spent, respectively, customers belong to this group is called “lost”, due to its score is the smallest score of 1 Table 2.1: Recency, Frequency and Monetary Score Description

Source: Wu & Lin, 2005

2 Customer Value Matrix Model

The model of Customer Value Matrix introduced by (Marcus, 1998) completely evolved from recency, frequency and monetary method, which is presented in table 2.2 This is a convenient table for a firm know well an interaction between two of three elements, such

as between F and M; L and R Value Matrix model is absolutely convenient for companies to easily analyze customer values in two formulas Each of them is four quadrants combined by both the average frequency and monetary values (F and M) and both the length and recency (L and R) value for details as shown in table 2

Table 2.2: Presentation of customer value matrix

Frequency (F) and Monetary

(lost relationship)

L↓ R↑

(establishing relationship) Source: (Marcus, 1998)

The second step is segmentation process after calculation of the average values of the purchase amount and amount spent on average Each customer is allocated into one of four resulting quadrants as illustrated in figure 2.1, which we can see information about two parameters that need calculating for the customer value matrix

Figure 2.1: Customer value matrix and its description

High

average amount per purchase

- Total amount of purchases

- Total quantity of customer

- Total sales revenue

- Average number of purchase = Total amount of purchases/ Total quantity of customers

Total sales/ Total quantity of customers

The next step of Customer Value Matrix process is comparison of Average Number of Purchases and Average Purchase Amount with total average values in each customer Finally, each of them is allocated into one of four quadrants with position name, such as best, spender, frequent and uncertain, which are depended on whether its parameters are higher or lower the axis averages

Length and Recency values

In current competitive market, customers are viewed as one of the biggest priorities of company To create loyalty and customer retention, companies need to identify their customer relationship based on some techniques One of them is customer relationship matrix that provides the management classification pursuant to many characteristics of four different groups between companies and their customers through two factors length and recency as depicted in figure 2.2 In conclusion, customer value is evaluated by customer value matrix or/and customer relationship matrix

Figure 2.2: Customer value matrix and its description

3 Customer lifetime value based on RFM

According to (Sunder, Kumar, & Zhao, 2016), CLV is calculated in various ways by scholars Customer lifetime value described as a fraction of cash flows using a weighted average of capital costs over the lifetime of a customer relationship with the company

To recognize and invest in potential customers, the calculation of customer lifetime value

average

Recency value

Potential Relationship RelationshipClose

Establshing Relationship

Lost Relationship

average length

average recency value

- Length (length of stay) = the number of days from the first visit date to the last visit date

- Recency = the number of days since the last visit

has become increasingly essential Estimating CLV supports company in some important decisions

Generally, there are various methodologies to calculate CLV for different organizations Based on arguments of (Safari et al., 2016), CLV estimated is based on the algorithm of RFM The selected characteristics pursuant on this method include latest purchase date

as Recency, the number of buying frequency during period time as Frequency, and total money spent by customers over period time as Monetary

Min-max method of normalization is used for the normalization phase This method performs on the initial data a linear transformation Suppose that maxA and minA are the maximum and minimum values of an attribute, A Then Min-max normalization maps a value, , of A in the range of [newminA, newmaxA] by computing in the followings equation:

Figure 2.3: The diagram of proposed model

As stated previous, how the paper takes an approach to address objectives of study is presented in figure 2.3 Besides RFM employed, generation rule is also considered to investigate more detailed customer behavior by each segment, which the method of association analysis is taken in to account

Long-term customer value is considered to be one of the quantitatively basic metrics belonging to the financial consequences of customer relationships with company This value can be a suitable benchmark for evaluating the company's efficiency and its financial markets Rather than products, it totally focuses on customers As the accessibility of information increases at the client stage, the value of client life can play

a crucial part in future marketing and corporate policy (Gupta et al., 2006)

4 Customer segmentation

As known, segmentation is a concept to divide overall customers into a subset with similar characteristics based on demographic factors or actions It also allows fleshing out data which put company in a stronger position to easily identify patterns as well as trends, gain a competitive edge and, demonstrate a deeper knowledge of your customers’ demands

With a deep understanding of how a company’s best existing customers are portioned, a business focuses on market to allocate and spend efficiently its valuable human and capital resources Customer segmentation provides other advantages which includes staying ahead of rivals in particular market sections and identifying fresh items that current and targeted customer might be keen on or improve products to fulfill many expectations of customer

In addition to the fact that companies strive to detect similarities and differences among customers into quantifiable segments as indicated by their demands, behaviors or demographics yet they also aim to determine the expected profit of each segment by analyzing its revenue they generate and cost of relationship maintenance It also supports

a company firmly propose better options and opportunities to customers who became the significant part of customer-company engagement and decide which segments are the most and least profitable to adjust their marketing budgets accordingly

As considered in the objectives, the market segmentation is concerned in this study As argued by many scholars, the market segmentation is one of the important methods to clarify customers into different classes It increases not only satisfaction applied in customer segmentation It is the process to separate heterogeneous behavior of customers into homogeneous groups, which is mainly based on common attributes and characteristics of customers Once customer segmentation is done, various marketing strategies on segments are applied to enhance the value of the customers and supported

to improve revenues of firms by retaining valuable customers Among segmentation methods, the clustering, particularly Two-Steps is employed and one of the popular methods to realize the homogeneous groups of customers and to carry out customized market strategies for each group (Liu & Shih, 2005)

5 Cross-selling products

Cross-selling indentifies products as additional and complementary package to attract consumers’s demand Cross-selling is prevalent in every type of commerce, including banks and insurance agencies Credit cards are cross-sold to people registering a saving account, while life insurance is commonly suggest to customers buying car coverage Therefore, Cross-selling products is to explore potential bundles of products that can take cross-selling to customers To do this, the method of ‘Association Analysis” is employed This method is to find out relationships of uncovering data to create competitive strategies Results is based on probability of products used at the same time

of customers, which the high probability is concerned on priority strategies (Wang & Keh, 2017) This means hidden data relationships are expressed to show a collection of association rules and frequent item sets

Cross-selling and upselling are similar in that they both focus on providing additional value to customers, instead of limiting them to already-encountered products In both cases, the business objective is to increase order value inform customers about additional product options they may not already know about The key to success in both is to truly understand what your customers value and then responding with products and corresponding features that truly meet those needs

CHAPTER 3: BIG DATA OF BANKING INDUSTRY AND

CONCEPTS APPROACHED

1 General information about the bank

Established on May 24, 1989 under the decision No 140/CT signed by the Chairman of the Council of Ministers under the name of VIETNAM EXPORT IMPORT BANK and being one of the first joint-stock commercial banks of Vietnam, the bank officially came into operation on January 17, 1990 On April 6, 1992, under license No 11/NH-GP signed by the Governor of the State Bank of Vietnam, the Bank was allowed to operate with a term of 50 years and its charter capital registered at 50 billion VND (equivalent

to USD12.5 million) and its name changed to VIETNAM EXPORT IMPORT COMMERCIAL JOINT-STOCK BANK (shortly called VIETNAM EXIMBANK) At present, Eximbank’s chartered capital is 8,800 billion VND The bank’s owner’s equity

is 13,627 billion VND, making it one of the largest commercial joint-stock banks by owner’s equity Vietnam Export Import Commercial Joint Stock Bank has a nationwide network with its Head Office located in Ho Chi Minh City and 124 Branches in Ha Noi,

Da Nang, Nha Trang, Can Tho City, Quang Ngai, Vinh, Hai Phong city, Quang Ninh, Dong Nai, Binh Duong, Tien Giang, An Giang, Ba Ria - Vung Tau, Dac Lac, Lam Dong and Ho Chi Minh city) VIETNAM EXIMBANK has established correspondent banking relationship with over 735 banks in 72 countries worldwide

2 Organization of the bank

3 Development orientations

Eximbank will take advantage of market opportunities to maintain sustainable growth, consolidate and expand its customer base heighten the position and develop Eximbank into a modern join stock commercial bank at which all shareholders, investors, customers stay assured with their capital investment efficiency and safety A bank that offers a wide range of high quality banking and financial products and services; and a brand name known to the banking and financial industry and making great contributions to the community and the society

4 Business activities

Products and services: With the motto of always keeping the leading position in reforming and diversifying the products financing, FX trading, and international settlement, Eximbank has been continuously studying to introduce to the market new products and services which can meet the demands of customers The main operations Eximbank is currently offering include: Savings — Deposit, Credit, Guarantee, Financial services for overseas studies, FX/Gold trading, Card activities, Financial investment, Others (Monetary and financial consultancy, Account inquiries…)

5 Evaluation of the capacity and the quality of Eximbank's products and services

Overall evaluation: First established among commercial joint stock banks in Vietnam, Eximbank has become one of the biggest commercial joint stock banks The image and brand name of Eximbank have become more and more widely known due to the Bank's development both in quantity and in quality Eximbank's size has continuously been increased with high growth rate since early years of establishment Eximbank has strengths in non-credit activities such as payment, guarantee, FXtrading, etc of which payment and FX trading are two operations which Eximbank is especially strong at compared to other peers To satisfy well the demand of its customers, Eximbank has identified that approaching and using modern banking technology is an important priority in its businesses Eximbank is one of the first banks to participate in the electronic clearing system of the SBV and one of the first 3 banks of Vietnam to be granted membership by two leading card organizations in the world which are MasterCard and Visa and has since then received lots of positive comments from these organizations

Eximbank is the first commercial joint stock bank to be selected to participate in "the banking modernization and payment system" organized by the SBV and financed by World Bank The cooperation project between Germany and Vietnam is also cooperating with and supporting Eximbank in the area of internal auditing In addition, correspondent banks such as Wachovia, Credit Suisse, etc also regularly share their professional experience and knowledge with Eximbank through the short term training seminars these banks organize.

Based on its strengths, Eximbank has become one of the typical commercial joint stock banks in terms of turnovers and sales in Vietnam Prestigious financial organizations in the world have very good impressions on Eximbank.Currently, Eximbank is attracting the interest of many local and foreign investors In particular, some international financial institutions are very keen on supporting Eximbank in modern banking governance With its qualified and experienced management board in the banking industry, and the achieve the target set strategies for which, Eximbank shall become one

of the leading commercial joint stock banks in Vietnam

Business results: Within the difficult and challenging business environment, the Board

of Directors and the Board of Management have by their detailed instructions together with endeavors employee preserve the business stability of the bank:

· Promoted the deposit and credit growth for larger market shares, while ensuring the prudent ratio in operations

· Improve the Net Interest Margin

as in the banking industry since the global financial crisis occurred and its aftermath lasted so far, Eximbank is not only confident to overcome challenges but also gradually affirms its position in the Vietnamese financial market

From Eximbank’s perspective, that is the foundation of sustainable growth, especially in banking operation Consequently, the annual report is regarded as a special publication which always receives the attention of the management of Eximbank and is self-made

by the Bank in terms of both content and form Specifically, as for the content, except