Intelligent Directory Search for Contact Centers: Gain a Competitive Edge

Contact center agents rely on the account information in their databases to answer customer questions and efficiently solve problems. They need a complete record of customer information, previous interactions with support staff, and purchase history. A clean database is necessary to fulfill this fundamental requirement. With user databases of thousands of millions of customers, automation and intelligent search is key.

The importance of a clean customer database

By the time a customer calls a support center, they are usually already frustrated and unhappy with your company. Whether a shipment is late, a defective product was delivered, or a service is underperforming, your contact center agents are beginning their interaction with an already irritated customer.

For the best possible outcome from every customer interaction, pulling up the customer’s data must be as quick and painless. Failing to find customers’ records, asking dozens of questions in order to find the right record, or only having partial records on-hand wastes your agents’ time and leads to yet more customer dissatisfaction.

Common customer database problems

One of the most common issues with customer databases is the prevalence of duplicate records. If a customer is unable to login because they’ve forgotten their password or used a different email, you could have more than one record for the same person. When they contact your staff to resolve a problem, your agents will only see part of the customer’s history.

Similarly, if a customer calls to follow up on a previous complaint, if the agent cannot quickly find the record of the previous call, or isn’t aware that there was one, they may create a new record. Not only does the agent not have access to the full picture, but you are also using up costly storage space with extraneous records.

Equally problematic is the linking of different customer information to one account. If Jane Smythe calls your support center and the agent mistakenly logs call notes on Jane Smith’s record, both accounts have been compromised and will lead to further confusion and frustration. This problem also occurs when automatic deduplication efforts merge records incorrectly.

Cleaning up your customer database

Many customer records are incomplete or contain contradictory information. A customer may have multiple shipping addresses and phone numbers, or use a different credit card for a new purchase. Unless your organization is a bank or credit agency, customers are unlikely to provide social security numbers, bank account numbers or other sensitive data that can be used to identify correlating records.

The only data field that you can consistently count on having is the customer’s name. While records should not be merged only because of identical or similar names, good fuzzy name matching will bring up potential matches. From there the system can attempt to automatically merge accounts with additional corresponding fields like birthdate, email, or phone number, and flag inconclusive matches for human review.

Preventing future database issues

Once a database is clean, the next challenge is to keep it that way. In these situations, a powerful directory lookup tool that can identify and link records across multiple systems and sources is worth the investment.

A database search tool with fuzzy name matching presents likely matches for each search query based on the match score threshold set by system managers. Possible matches are ranked from most to least likely, allowing staff to review the results and ask the appropriate follow-up questions to find the right record faster. Without fuzzy matching, these potential matches can be missed and agents are more likely to create duplicate records and work with incomplete information.

The challenge of matching names

Comprehensively cleaning a customer database, and preventing future errors requires intelligent, deep understanding of names, enabling a simple search query to find potential matches in the database regardless of common sources of confusion like nicknames, misspellings, names split inconsistently across database fields and more.

Take for example the name Caitlin Murray Smithe. Legacy tools would only find Caitlin’s name in a database if the query is an exact match to the record. Your customer database search and deduplication systems must recognize the similarity of Katelyn M. Smithe, Cait Smith, Smithe, C. M., and more without relying on a simple list of potential variations that must be constantly updated and will inevitably have holes.

Learn more

Fuzzy name matching enables intelligent records cleaning and improves the accuracy of records search, ensuring that agents find the correct record on the first try, providing better customer service, preventing workflow disruption, and saving time and money.

Ready to utilize fuzzy name matching to clean and maintain your customer database? Basis Technology’s Rosette text analytics combines string matching with phonetic comprehension, etymology, onomastics and machine learning to create the ideal fuzzy name matching system for customer records. Rosette’s trusted blend of machine learning and traditional name matching techniques has improved name search for the world’s thorniest name matching challenges for over 15 years. Talk to our sales team about a demo or trial of Rosette fuzzy name matching for customer databases.