DataGYM » Showcase » Case Studies » Real Time Customer Profiling

FACT SHEET
Richardson, Texas; May 10, 2000

Instant Decisioning Engine based on CIANT DataGYM

Real Time Customer Profiling for 1-to-1 Marketing Results

How do you create a good impression on a new prospect or a customer on the web or over traditional channels? Reduce chance encounters that result in missed opportunities to create lifetime value for an existing customer or new prospect:

• Treating customers as strangers can make them strangers.
• There is a lot that can be learned from the obvious data customers provide in each interaction.
• There is a lot that can be deduced from the data provided by a prospect in the first chance meeting.
• New data + old information = triggers for effective communication in any business.

Clients and customers are using multiple channels to reach businesses. World-class service is based on identifying a Customer whether they expect it or not, and being able to communicate to them about their needs, not just your products or services.

There is a fine balance between how much data can be requested of an individual on-line and the point at which the prospect or customer will click "out of site". CIANT’s Instant Matching Engine allows you to take limited information from a prospect or customer and leverage it against existing data for maximum marketing affect.

There are four steps to this real time process:

• Identify all that can be identified from an incoming stream of data (example an input form).
• Relate this data to the information that exists already within a business
• Develop an understanding of the prospect or customer, execute rule-based algorithms to decide what and how to communicate.
• Communicate relevant message(s) to the individual.

CIANT DataGYM based Instant Decisioning Engine provides these real times decisions.

The DataGYM™ Instant Decisioning Engine attempts to provide such solutions through a database environment where a server is connected to an Internet or Intranet environment behind firewalls and other protective layers. This server is designed to accept any number of data elements that are parsed and compared against a stored database of information. The parsing includes country specific data, using language rules specific to a local market. Probabilistic algorithms are used to match incoming data to the existing data. The result, which might include one or more records from the database executes decision rules and returns a real time decision to the prospect or customer.

There are three components in a DataGYM™ Instant Decisioning Engine:

The Input Process – accepts and standardizes data for input to the Instant Decisioning Process,.creates a number of Phonetic-Key(s) (based on a proprietary Phonetic Algorithm) and invokes the Instant Decisioning Process.

Facts:

The Instant Decisioning Process – extracts all information from the database that might potentially match the input data and pairs this data based on a customized sequence. There are a number of matching algorithms based on probabilistic and lingual references. All these can be changed and customized based on country of application or on Client’s requirements.

Facts:

•  Phonetic use of language to allow spelling distortions and variations.
• Probabilistic algorithms to determine match probability.
• First Match/All Match/Best Match options.
• Unlimited number of match hierarchy and unlimited number of match source tables.
• Nick Name tables and criss-cross matching allows you to match data that might have been misassigned.
• Phonetic Tables can be changed for each market due to language rules.
• Match data can be given different weights to emphasize particular words
• Identify household and demographic information based on the matches observed and use it in rule based decision tables to drive decisions.
• Use decisions to drive customer/prospect touch points be it web application or call center or IVR.

The Output Process– As soon as there is a match, the decision algorithms are executed as above and returns the decision to the prospect or customer via this process.

• Return first match with probability
• Return all matches based on importance and probability.
• Return best match based on importance and probability.
• Ability to execute C/C++ functions for decision rules.
• Customizable to return decision to various System environment.

There are two other components required to establish and maintain the Customer/Prospect database for the Instant Decisioning Engine:

DataGYM Conversion :

Used to clean, parse and standardize data before loading it into a data repository.

DataGYMHouse-holding :

Used to establish all the phonetic rules, matching hierarchy and matching data source details.

Instant Decisioning makes the 1-to-1 marketing hopes and dreams a reality. This environment allows everyone doing business over the Internet, telephone or traditional Telesales organization to leverage this platform.

Like the Instant Decisioning Engine, the DataGYM platform can be used for Fraud Matching purposes real-time or can be configured for a variety of web based applications. Examples include Vertical Market Exchanges for credit accreditations and profile preferences; internet interface with wireless and cell phone devices; web site visitor cross-sell; and instant profiling of prospects over web or call center for tailored offerings to maximize loyalty.

 Back to top of page