By Dr. Sophie Harbisher
Kani Payments
One of my favorite topics, and the thing I'm asked about often, is smart data. But it's a somewhat misleading phrase; data isn't inherently smart or not. What we are really talking about is how you use data, because if you build the right processes and pipelines around data, it becomes a strategic business asset—that's the smart bit. So, how to harness data so you can be smarter in leveraging it …
The first part of any process involving data is to make sense of it. By cleansing raw data businesses can ensure consistency and accuracy, which allows for easier comparison across multiple sources. Only then can you extract meaningful insights and use data for both internal use and to meet external regulatory requirements.
You should aim for the ability to standardize data from many different sources into a common language. This makes the reconciliation and reporting process much more effective, eliminating the need for time-consuming (and avoidable) downstream data work.
Ideally, data should come from multiple sources, such as processors that work with issuers of Mastercard or Visa cards. Their transaction data is then pulled into the system of the company that does data monitoring and reporting. Typically, processors provide data in their own format. The monitoring and reporting company takes data from multiple files provided in various formats and imports it into a database, which structures the data. An additional standardization layer allows for use of all available transaction data for reporting. Making it accessible via easy-to-use dashboards will give clients a standardized view so they can query all their data in one place.
Once you're working smarter—not harder—with your data, you will gain the holistic view that should be the main objective of your data strategy, especially if you're working with multiple payment processors. One processor might give you a CSV file, another an XML file, and another a PDF or text file. In-house finance teams generally don't fully understand these different file formats, or how to open them and get the information they really want. The right solution can do all of this for you.
Put simply, it matters because it saves time and money. A robust data governance framework means finance teams don't need to spend all day making sense of data through manual, time-intensive data analysis tasks. A data monitoring and reporting platform provider can import files in a few seconds, map it into a single schema and produce actionable analysis.
Teams don't have to go through thousands of files before their data is usable and can instead concentrate on jobs that add real business value.
With smart processes, you can interrogate the data and underlying trends in cardholder behavior. Examples include looking to see what cardholders are spending, where they are spending and what method they are using (chip and pin, contactless, online purchases, etc.). Having standardized data provides much more flexibility when reporting on these metrics.
Once the data is easy to work with, you can generate custom reports for tailored business insights. One report, for example, could look at supermarket spending, where you could see the effect of lockdowns as people shifted from smaller, more frequent shops to a more substantial weekly one. Building these custom reports would be a laborious job using in-house resources.
Effective data standardization processes also speed up investigations and rectify anomalies in reconciliations. With so many different files and data sets involved across multiple sources, it's common for some data fields to be missing. Or perhaps a processor generates data columns named in a certain way (such as transaction date, currency and transaction amount), while another might use a random code for that same column. These differences create issues with reconciliations.
If you tried to investigate those differences in-house, you'd have to look through each processor's specifications document and figure out each column in each data set to find what they were looking for. Advanced standardization practices resolve that by looking for certain transaction elements, such as dates, amounts or how the transaction was authorized.
Data science will become increasingly mainstream as people become more aware of techniques such as machine learning, especially given the uptake of ChatGPT and other large language models. More interest in these areas will lead to more research, development and interest in potential applications.
Data monitoring and reporting in the payments industry revolves around delivering solutions for companies to gain the most value out of their data. Data is also starting to be mapped to wider economic data, like GDP figures or other macroeconomic data, to provide more intelligent insights and benchmark against the wider industry.
Looking further ahead, I expect different statistical models or machine learning models will be used for more accurate forecasting. You might have a set of cardholder spending at a certain point in time, but how will that look six months from now?
That's the next step to gain more useful information out of your data and then use it to help drive management decisions. 
Dr. Sophie Harbisher is the Data Science Lead for the Kani Payments platform, overseeing data modeling and reporting. Prior to joining Kani Payments, Sophie worked as a postgraduate research student in Bayesian statistics at Newcastle University, during which she completed a 3-month placement at IBEX Innovations. Contact her at Sophie.harbisher@kanipayments.com..
The Green Sheet Inc. is now a proud affiliate of Bankcard Life, a premier community that provides industry-leading training and resources for payment professionals. Click here for more information.
Notice to readers: These are archived articles. Contact names or information may be out of date. We regret any inconvenience.
Prev Next
