Business Intelligence and Data Mining to Support Sales in Retail

38.2.1 Online Analytical Processing (OLAP)

Online Analytical Processing (OLAP) is an approach to quickly provide answers to analytical queries that are multidimensional in nature. The typical applications of OLAP are in business reporting for sales, marketing, management reporting, business process management, budgeting and forecasting, financial reporting, and similar areas. In the core of any OLAP system is a concept of an OLAP cube (also called a multidimensional cube or a hypercube) [7, 9]. It consists of numeric facts called measures which are categorized by dimensions. The cube metadata is typically created from a star schema or snowflake schema of tables in a relational database. Measures are derived from the records in the fact table and dimensions are derived from the dimension tables [8].

38.2.2 Release and Express Technology

The UK Consumer Cards and Loans business within Barclays Bank, for example, spent five years executing its plan to apply analytics to the marketing of credit cards and other financial products. The company had to make process changes in virtually every aspect of its consumer business: underwriting risk, setting credit limits, servicing accounts, controlling fraud, cross-selling, and so on. On the technical side, it had to integrate data on 10 million Barclaycard customers, improve the quality of the data, and build systems to step up data collection and analysis. In addition, the company embarked on a long series of small tests to begin learning how to attract and retain the best customers at the lowest price. And it had to hire new people with top-drawer quantitative [9].

38.3.1 Data Mining Forms and Cycle

Data Mining comes in two forms: directed and undirected. Directed data mining attempts to explain or categorize some target fields such as income or response classification, estimation, and prediction. Undirected data mining attempts to find patterns or similarities among groups of records without the use of a target field or collection of predefined classes, as examples of undirected tasks are affinity grouping and clustering [10].

Data Mining provides many different techniques to extract knowledge from data. It is a multidisciplinary field of research that has many extremely useful applications. At the present time the techniques are becoming more commonly used but have not been applied adequately in the store layout. Store layout problem is motivated by applications known as market basket analysis to find relationships between items purchased by customers [12]. The store layout is an important retailing decision that can help or harm sales and store profitability. Store layouts are extremely important because they strongly influence in-store traffic patterns, shopping atmosphere, shopping behavior, and operational efficiency. Store layout design can play a key role not only in satisfying buyers’ requirements but also in influencing their wants and preferences. Store layout affects consumers’ price acceptability, which is positively related to purchase intentions [13]. They also report that superstores are currently revolutionizing the nature of retail service, mainly by creating more effective self-service arrangements as a result of improvements in store layout design [12].

38.3.2 Data Warehouse

Data warehouses collect and coalesce data from across an enterprise, often from multiple transaction-processing systems, each with its own database. Data is gathered because it is needed for some operational purpose, such as inventory control or the billing and, once it has served that purpose, it languishes on disk or tape or is discarded [10]. Analytical systems can access data warehouses. Data warehousing may be a facilitating technology of data mining. It is not always necessary, as most data mining does not access a data warehouse, but firms that decide to invest in data warehouses often can apply data mining more broadly and more deeply in the organization [14]. For example, if a data warehouse integrates records from sales and billing as well as from human resources, it can be used to find characteristic patterns of effective salespeople.

The goals of an initial data warehouse implementation should be specific, achievable, and measurable [11]. Building and using a data warehouse is a complex task because it requires business skills to understand how systems store and manage their data, technology skills to understand how to make assessments from quantitative information and derive facts based on conclusions from historical information in the data warehouse and program management skills to answer the need to interface with many technologies, vendors, and end-users in order to deliver results in a timely and cost-effective manner [11].

Data warehouse administration includes data refreshment, data source synchronization, planning for disaster recovery, managing access control and security, managing data growth, managing database performance, and data warehouse enhancement and extension [11].

Firstly, having a data warehouse may provide a competitive advantage by presenting relevant information from which to measure performance and make critical adjustments to help win over competitors. Secondly, a data warehouse can enhance business productivity because it is able to quickly and efficiently gather the information that accurately describes the organization. Thirdly, a data warehouse facilitates customer relationship management because it provides a consistent view of customers and items across all lines of business. Finally, a data warehouse may bring about cost reduction by tracking trends, patterns, and exceptions over long periods in a consistent and reliable manner [11].

38.3.3 Market Basket Analysis

Market basket analysis (MBA) is used to determine which products sell together. The input data to a market basket analysis is normally a list of sales transactions, where each has two dimensions, one represents a product and the other represents a customer, depending on whether the goal of the analysis is to find which items sell together to the same person [13]. The main aim of MBA in marketing is to provide the information to the retailer to understand the purchase behavior of the buyer, which can help the retailer in correct decision-making [15]. MBA is transaction data that describes three fundamentally different entities: customers, orders, and items [10].

In a relational database, the data structure for market basket data often looks like Fig. 38.1. This data structure includes three important entities [10]:

Open image in new window

• The order is the fundamental data structure for market basket data. An order represents a single purchase event by a customer. This includes the total amount of the purchase, the total amount, additional shipping charges, payment type, and whatever other data is relevant about the transaction.

• The item table also typically has a link to a product reference table, which provides more descriptive information about each product. This descriptive information should include the product hierarchy and other information that might prove valuable for analysis.

• The customer table is an optional table and should be available when a customer can be identified, for example, on a website that requires registration or when the customer uses an affinity card during the transaction.

MBA is a technique that assists in determining which sports items are purchased together according to the association rules, primarily with the aim of identifying cross-selling opportunities. Its primary objective is to improve the effectiveness of marketing and sales tactics using the customer’s data [16]. Supposing a manager of a sports store wants to learn about the buying habit of the customers so that it can be determined which groups or sets of items customers are more likely to buy from the store. One plausible option to determine this is by performing market basket analysis on the retail history, i.e., the retail data collected from previous transactions. The main application of this analysis is in optimizing the store layout, where the items that are likely to be sold together can be placed closer to each other [16].

38.3.4 Association Rules

Given a set of records (i.e., transactions), each of which containing several items from a given collection, the goal of association-rule discovery is to produce dependency rules that can predict the occurrence of an item based on occurrences of other items [18]. For example: A store manager may wish to know how likely a customer would buy a tennis ball if he buys tennis rackets. Such knowledge can help the store manager in product arrangement, shelf space planning, and effective implementation of product promotion strategies. The items that co-occur frequently can be discovered from a customer transactions database using association rules [16].

The applications of data mining in retail trade enterprises are mainly concentrated in association rules mining. Association rule mining is an initial data exploration approach that is often applied to an extremely large data set. An example is grocery store market basket data. Association rules mining provides valuable information in assessing significant correlations. By mining association rules, marketing analysts try to find sets of products that are frequently bought together [12].

38.3.5 Cross-Selling and Up-Selling

Cross-selling is an old and valuable technique used by salespeople to increase order size and to transform single-product buyers into multiproduct ones. Cross-selling involves the sales of additional items related (or sometimes unrelated) to a previously purchased item, while up-selling involves the increase of order volume either by the sales of more units of the same purchased item, or the upgrading into a more expensive version of the purchased item. Rather than relying on a sales or services representative to decide whether to cross-sell and which item to offer, modern cross-selling utilizes analytical tools to study the customer’s past behavior, correlate this information with similar customers, and then identify potential cross-selling opportunities at each contact with the customer [19].

This information advantage, added with the higher costs of switching, produces a virtual local monopoly for the firm, which is then better able to compete for its customers than other firms that do not have an established relationship or access to the same information about their needs and preferences. For these reasons above, many customer-focused enterprises are taking advantage of cross-selling as a tool for customer development [19]. While implementing these cross-selling strategies, firms realized that cross-selling is more effective in inbound than outbound customer contacts. In other words, it is better to cross-sell when the customer calls the firm than to call the customer for the purpose of cross-selling. Some of the reasons for this important finding are intuitive. First, costs are lower, as the contact is initiated by the customer, and there is no waste in reaching the customer. Second, since the customer initiated the contact, the mindset is already centered on the firm and its services, simplifying the sales task. Third, if the customer called with a problem and it is solved to their satisfaction, the customer is more receptive to the cross-selling suggestion, particularly when this suggestion meets their needs. The analytical tools for cross-selling reviewed so far focused on identifying the “next-to-buy” or “next-to-offer” service, based on “natural” acquisition sequences observed across customers and over time [19].