Many financial institutions (FIs) are considering merchant payment cleansing as a key ingredient to a data strategy. Merchant Payment Cleansing takes a dirty raw transaction string and identifies a cleansed business name, along with assigning an appropriate business category. Merchant payment cleansing is a critical tool to help FIs better understand customer transaction behavior and model spend patterns. An FI can leverage this clean, tagged data to provide a more organized online banking experience, avoid transaction disputes by providing better online banking statements, and reduce IT man hours, lag time and quality issues.
For FIs who are beginning to evaluate a merchant payment cleansing solution, this short guide outlines the four most important factors to consider when choosing a vendor.
Match rate describes the percentage of transactions for which a cleansed business name and category is provided. Match rate is typically the first metric that FIs will evaluate. After all, who doesn’t want to get as many transactions cleansed and categorized as possible? It’s an important metric, but beware that it can be deceiving – a match rate approaching 100% sounds impressive, but it might be too good to be true and should prompt these important questions:
Financial institutions should look beyond what is on the marketing slick and evaluate which merchant payment cleansing vendor can deliver the best match rate on it’s data. The proof is in the pudding.
Segmint’s merchant payment cleansing service leads the industry in efficiency, accuracy and reliability.
Match rate is important, but not the be all and end all. Once you’ve determined a realistic match rate that you can expect, a second important factor is the speed in which that match rate can be delivered. Ideally, you want a solution that can deliver the lion’s share quickly after a short training period on your specific data.
Segmint’s extensive transaction knowledge base and human supervised AI delivers accurate results quickly. Segmint recently completed a project with a large government financial institution where more than one trillion dollars in transactions were classified in a single day.
It’s easy to classify a business to restaurants. It takes more effort to categorize all the restaurants based on cuisine or style. After all, a high-end steakhouse is different than a family restaurant. ‘Shopping’ can describe many distinct purchases – a transaction at a men’s clothing store, a women’s clothing boutique or a home furnishings store. Specific categorizations make a difference.
Taxonomy can also reflect other attributes of a purchase. For example, identifying transactions as recurring subscription payments could allow a financial institution to know which of it’s cardholders use it’s product as their primary card and which customers are most sticky.
Financial institutions should demand that a merchant payment cleansing vendor deliver specific categorization into a robust taxonomy so the cleansed data can help the FI make strategic decisions.
For over a decade, Segmint’s taxonomy and categorization knowledge base has been curated by a team of advanced-degree library scientists. In a recent merchant cleansing bake-off, Segmint delivered 10x more categories as the next competitor with better speed and quality.
Privacy of customer or member data is a major concern for any financial institution. A merchant payment cleansing solution should not put customer data at risk.
Segmint’s data cleansing process does not require any personally identifiable information (PII) – in fact, we won’t even accept it. Our patented capability to exchange anonymized transaction data keeps your customer data safe and secure.
Merchant payment cleansing can play a vital role as the foundation of an organization’s data strategy. It is impossible to truly understand every transaction string, but FIs should expect more from their merchant payment cleansing partners than they are getting today. FIs should evaluate vendors carefully and find a partner who will deliver the match rate, speed, quality, and privacy to build the groundwork for a solid data game plan.
