It’s no secret that loan processes are paper-intensive and requires much back and forth between banks and those applying for loans. It doesn’t matter if it’s private or business loans, in any of these applications a lot of documents get involved. The information on these documents is crucial for accepting or refusing a loan. So any credit analyst must deal with them. But what makes them a nightmare to process? Let’s have a look.
In credit processing, a lot of different agreements and addendums are needed: loan proposal, irrevocable od splendor, income statement, payout documents, renovation invoices, waiver of rights, know your customer documents, … There is a lot of crucial information involved.
To start with: these large volumes are not easy to categorize and organize manually. Furthermore, the information from these documents need to make it to whatever in-house system you’re using, because it needs further processing and is crucial for decision-making.
Since more than 80% of these documents are unstructured, it requires a lot of manual work to classify them, interpret and extract data from them.
To fill in processing gaps, banks are adding more and more people to their teams. As a result, these processes remain extremely decentralized and expensive. Manual data entry also increases the likelihood of clerical errors. Furthermore, it’s not a fun job either and banks are already struggling in their war for talent.
With loan indexations coming up, the disadvantages of manually processing credit applications will only get bigger. According to a recent study from McKinsey, more than 50% of business leaders are prioritizing the automation of documents and incoming emails. So let’s have a look at what it means to automate these processes.
To cut this manual work, banks have been trying to automate these tasks with technologies like RPA. Robotic Process Automation has been around for a while, but what is it exactly? RPA creates scripts that automate routine, predictable tasks. It’s a rule-based approach to automation that mimics the actions of a human by performing mouse clicks. RPA is great and it works very well for simple, well-defined tasks. But there is no intelligence built into RPA. This means that for all these unstructured documents, this technology will fall short. Banks are realizing that simply implementing an RPA tool doesn’t necessarily translate into automation success. That’s where Intelligent Document Processing comes in.
What is Intelligent Document Processing?
Intelligent Document Processing or IDP is a tech solution that uses artificial intelligence to automatically classify and extract information from documents. It’s intelligent because it uses artificial intelligence (AI) to do so. AI trains machines to mimic human intelligence so they can complete repetitive or complex tasks for us or predict outcomes. IDP uses different AI-technologies to automatically process documents. Machine learning (ML) is the process of using patterns in data to ‘teach’ the machine, so its performance and prediction become more effective and accurate over time. Natural language processing (NLP) is the branch of AI focused on leveraging ML techniques so the machine can understand and interpret human language. So, in the case of Intelligent Document Processing, machine learning and natural language processing are used to train a computer to simulate a human subject matter expert’s review of a set of documents.
A computer capable of understanding the contents of documents, including the contextual nuances of the languages within them. The technology can then accurately extract information and insights contained in the documents as well as categorize and organize the documents themselves. Because of its intelligence, banks are able to automate the classification and data extraction from every possible document and email type.
So instead of having to manually interpret every incoming document and email, Nanou her team at Bank van Breda would be able to automatically do so using IDP. The information that comes to their credit analysts is then already pre-processed and they can dive into the analysis and decision-making process straight away. Saving between 10 to 30 minutes per credit file.
Curious to know more about how IDP can help credit teams work smarter, faster and happier? Here are some resources to check out for more information: