Contact Center Solutions Featured Article

IBM Simplifies, Customizes Predictive Analytics Software

May 19, 2010

IBM has come out with new predictive analytics software that with three simple clicks, business users can now build predictive models within configurable Web browser interfaces, and run simulations and "what-if" scenarios that compare and test the best outcomes before the models are ever deployed into operational systems.


The IBM SPSS Decision Management solution gives business users now have full control over the analytic process, enabling them to make accurate decisions in real-time, based on changes in strategy, customer buying patterns and behaviors, or fluctuating market conditions. The new product has two versions: one that manages customer interactions via contact center, web, point-of-sale or e-mail and the other specifically designed to help identify fraudulent claims in the insurance industry, which accounts for approximately $30 billion in losses a year. 

The IBM SPSS Decision Management solution combines predictive models,business rules and optimization to increase an organization's confidence to automatically deliver accurate, high-volume, high-value decisions at the appropriate point of customer interaction.

For example, says IBM, a retailer may need to decide which customers should receive information about a new line of products. The marketing manager can quickly build a model identifying the customers likely to respond - based on past purchasing patterns, demographics, responses to previous offers - and include those customers in the new product campaign. However, before deploying the results the business user can first "tweak the dials"using a simple web interface, and run what-if scenarios on the results. This ensures the campaign will yield optimal resultsby targeting high-value customers.

With the new solution, business users can set up data for quick and efficient modeling, select the best-performing models automatically and then get results in easy-to-interpret charts and graphs. Predictive models can be deployed in a fraction of the time it would take to build them manually. And, with a new simulation feature enterprises can visually see the outcomes and do a comparison of the models and business rules, and change if necessary, before they are deployed.

This solution also enhances collaboration between business users and professional analysts by providing one framework to work together seamlessly. Users can easily design and build models based on their own scenarios, with their expert analysts validating and refining those models to improve results.

According to Forrester Research, about 60 percent of companies evaluate their capabilities to be poor/below average for customer interaction management, and 62 percent cannot easily manage real-time scoring of customers. The new IBM SPSS Decision Management software for customer interactions helps organizations retain customers, grow revenue and drive profits by creating a personalized experience for every inbound customer and prospect. Users can now quickly and easily determine which inbound interactions are the best candidates for an up-sell, cross-sell or retention offer and then offer personalized, real-time recommendations that have the greatest likelihood of acceptance by individual customers.

For example if a high-value retail banking customer calls into the contact center to complain about a product or service,the new software may predict, based on the customer's data, that the individual is likely to churn. The information about the complaint, combined with the customer's history, can then be used to create a customized retention offer on the spot.

At the same time IBM SPSS solution helps firms address another but unsavory and costly type of interaction: fraud. The Insurance Information Institute reports that  fraud accounts for 10 percent of the property/casualty insurance industry's incurred losses and loss adjustment expenses, or about $30 billion a year.

With the new IBM SPSS Decision Management software for claims, insurers can easily reduce settlement time and increase customer satisfaction through automated, real-time risk assessment. Claims adjustors and others with in-depth business knowledge can quickly and easily define how risk should be assessed and automate the decisions made by the contact center agent - who is directly speaking with a customer - to easily determine whether a claim is fraudulent.

For example, by using a combination of business rules and predictive models, the insurer can set up processes to identify claims that qualify for quick approval as well as those that seem suspicious and require follow up. This means they can resolve most legitimate claims in a single interaction - increasing customer satisfaction and decreasing costs - and detect fraudulent cases at an earlier stage so that they can be routed for investigation.

"IBM Business Analytics software delivers complete, consistent and accurate information that decision-makers trust to improve business performance," said Rob Ashe, general manager, business analytics at IBM.  "By making predictive analytics pervasive and giving business users control of the technology organizations can optimize the point of interaction, better anticipate change in real-time, and carry out strategies that improve outcomes. We have empowered every single business user with the power of predictive analytics, so the best course of action can now be easily deployed into any operational system, minimizing the cost of bad decisions."


Brendan B. Read is ContactCenterSolutions's Senior Contributing Editor. To read more of Brendan's articles, please visit his columnist page.

Edited by Stefania Viscusi



Home