BACKGROUND: HSBC Bank USA, a member of the global HSBC Group, serves more than 1.4 million retail banking customers, providing a variety of checking, investment, loan and other financial products through 380 New York banking locations. HSBC Bank USA has $35 billion in assets and also serves business and commercial customers.

PLATFORMS: Windows NT on a network of Compaq DeskPro PCs and a Novell server.

PROBLEM SOLVED: There is no shortage of banking opportunities for today's consumers ­ our job is to make sure more people choose HSBC's products rather than going to the bank down the street. To do that, we must know more about our customers so we can be there with the right information when they are ready to make a particular purchase decision. In the interest of our costs and their patience, we want to deliver only the marketing messages that most interest them. Data mining with SPSS gives us the power to do both. In the three years we've been mining our data, we've increased sales across our product lines at least 15 percent and as much as 50 percent by uncovering cross-selling opportunities and retaining more customers.

PRODUCT FUNCTIONALITY: The regression and clustering capabilities in SPSS are outstanding. Overall, SPSS is perfect for database marketing and exploratory data analysis and is miles beyond traditional OLAP reporting. SPSS lets us uncover relationships hidden in our 35GB customer database, determine how strong a particular statistical relationship is and do "what-if" scenarios to find out what that means in terms of a business opportunity. For example, using SPSS, we can mine our sales data for the specific characteristics of people who, in the past, bought a new car once their auto loan matured. Then we can look at current auto loans that are about to be paid off and predict which customers will soon be shopping for a new car ­ and a new loan. That kind of predictive analysis helps us contact the right people at the right time with the right offer.

STRENGTHS: SPSS is intuitive to use and programming knowledge is not necessary. I can concentrate on my analysis, not my syntax. Despite its ease of use, I don't have to give up power ­ SPSS gives me an outstanding depth and breadth of analytical functionality. In addition, senior managers like it because you can easily walk them through the models. You don't need an extensive statistical background to understand the results.

WEAKNESSES: Data handling capabilities at the mainframe level could be better; but we've evolved over the years to using mostly minicomputers and PCs, so this hasn't been a problem for us.

SELECTION CRITERIA: We needed a product that balanced ease of use and statistical power. SPSS provides just that ­ plus, the sales benefits of just one good model can easily pay for the product. I've been using SPSS for more than a decade, and I've never found anything better for my needs.

DELIVERABLES: I create predictive models with SPSS and present them to decision-makers and salespeople in the product lines, giving them the information they need to help them more accurately anticipate customer needs. SPSS enables me to create a graphical description of my model, export it directly to PowerPoint and create a presentation that's easy for anyone to understand. They can quickly see, for example, the relationship between the repeat car loan customers and a universe of customers that "look like" them, so the future opportunity becomes very apparent.

VENDOR SUPPORT: SPSS spends the time with me that I need to solve any problem or issue ­ they really understand my business and my needs. My account executive is proactive and checks in periodically to keep me informed or just to see how things are going.

DOCUMENTATION: Both printed and online documentation are extensive and easy to follow. In addition, the company's Web site has been a good resource for me and includes test data sets that enable me to run examples from the manual on my PC.

Register or login for access to this item and much more

All Information Management content is archived after seven days.

Community members receive:
  • All recent and archived articles
  • Conference offers and updates
  • A full menu of enewsletter options
  • Web seminars, white papers, ebooks

Don't have an account? Register for Free Unlimited Access