Residential mortgage servicing, the process of collecting your mortgage payments and passing the right amounts to investors, tax authorities, and insurers is probably not the first industry you would think of as a hotbed of digital transformation.
After you close on your home loan, the mortgage servicer is your point of contact for anything and everything related to paying off your mortgage. For most of us, that is where the payments go until perhaps the servicing rights are sold to a third-party servicing company like Select Portfolio Servicing, Inc. (SPS). We then go through the process of changing mailing addresses and account numbers. Other aspects of loan servicing, such as bankruptcy, foreclosure, property taxes and insurance, payoffs, and dispute resolution, are also part of the servicer’s responsibility.
This story is about SPS, a residential mortgage servicing industry leader that is a wholly-owned subsidiary of Credit Suisse Group, AG.
I met with Jay Nair, senior vice president, financial services at Infosys. He says this example had two vital ingredients for digital success – the first being a visionary leader in Randhir Gandhi, SPS CEO, who is dedicated to significantly improving the customer experience and operational efficiency. Also required is a trusted partner in Infosys, a leader in next-generation digital services and consulting to help navigate the digital transformation.
The story told to me by Mr. Gandhi of SPS is impressive, and I hope it inspires your digital transformational journey, regardless of your industry.
Improving the customer experience
SPS and Infosys have been working together to transform the paper-intensive mortgage servicing industry digitally. SPS is improving the customer experience by translating documents into data points and data points to usable information.
Utilizing artificial intelligence (AI), machine learning (ML), and natural language processing (NLP) on the petabytes of data created with each customer touchpoint through various channels, be it the mobile application, written correspondence, website, phone calls, and then collating and correlating those data points is improving the customer experience.
In addition to improving the customer experience, companies will likely find other benefits as they go through the digital transformation process, including reducing costs and risks related to manual processes, compliance, and oversight.
The Infosys relationship
Choosing a technology partner is an important decision. If you embark on the journey without a trustworthy partner who can deliver results, life gets exponentially more challenging. Most companies need to focus on the core business. Technology will be integral to the success, but it cannot be the core business, so you need a partner to achieve results.
SPS chose Infosys for several reasons:
- A relationship spanning 17 years with high-level management support
- Infosys brings to the table a cloud ecosystem (Infosys Cobalt) that includes world-class partners such a Microsoft and the ability to deploy people with Azure expertise
- Most importantly, a track record of execution because all this means nothing unless it can translate to results.
- Global footprint providing critical 24/7 support
Infosys Mortgage Solutions, part of Infosys Cobalt, encompasses business process automation solutions for the mortgage industry, with a primary focus on document-centric processes that are manual and effort-intensive. These solutions are built on open-source and employ state-of-the-art techniques like computer vision, NLP, and machine learning, including correlation, predictive analytics, and classification. Infosys Cobalt is a set of services, solutions, and platforms for enterprises to accelerate the cloud journey. It offers 14,000 cloud assets and over 200 industry cloud solution blueprints.
Data from paper
SPS services over one million US customers, with over 1,200 data points per customer!
All the data points must be validated and matched with the documentation that comes along with each loan. Working with Infosys, a document repository was created based on a private cloud using Microsoft Azure.
The data files are populated by ingesting documents in real-time. Exceptions are flagged for SPS associates to intervene. Documents, especially proprietary written correspondence and loss mitigation documents, are not uniform in this industry.
Translating PDF documents into data is achieved using optical character recognition (OCR). However, in many cases, it might be a copy of a fax that is virtually unreadable by OCR, where artificial intelligence (AI) algorithms along with machine learning (ML) and natural language processing (NLP) are the solution.
SPS worked with Infosys to produce unique NLP and AI algorithms to solve this problem. The result is that SPS knows from an accuracy standpoint the data is rock solid.
By taking advantage of this technology platform, SPS efficiently achieved significant portfolio growth without sacrificing its commitment to absolute compliance, all while improving the customer experience.
From a customer experience standpoint, SPS can ingest massive amounts of data-intensive documents and make that data immediately useable by customer service agents. This reduced the service transfer timeline for customers by over 95% – creating a uniquely seamless service transfer experience.
A 360-degree view of the customer
Once SPS saw the first project’s success, the next element was to add data from more sources.
SPS sends out millions of letters and makes millions of calls every month. Other customer touchpoints include the mobile application and the website. Like many companies that have grown organically, the data resides in various back-end databases.
SPS worked with Infosys to build a dashboard on top of this massive data repository. SPS has visibility into logs from the application, clicks on the website, every phone call inbound or outbound, every document sent to the customer, or sent by the customer to SPS.
Equally importantly, SPS has customer payment behavior, customer questions, and customer disputes. With AI algorithms, SPS has created a 360-degree customer view. With insights into customer behavior and what might happen next, SPS can now respond proactively and provide the customer with options designed to result in the best possible outcome. If the customer is still not entirely on track, SPS identifies these outliers, and management can intervene if necessary.
It is now possible to score every loan and identify those in a high-risk category, with action items as to why the system thinks the customer will call and for what reasons.
That is just mind-blowing from a customer standpoint, and the response has been positive. Customer service agents and the customers are completely in sync from the beginning of the call because the system has already prepared the agents with the information customers will ask for and provided the best possible options to resolve each customer’s situation. This has resulted in improved customer satisfaction scores across the board, a reduction in repeat calls, and improved confidence for customer service agents who can quickly develop a rapport with customers by providing them with solutions that fit their needs.
It would be impossible without using technology and AI tools to turn the data into useable information.
The Texas Freeze of 2021
SPS worked with key partners and an insurance company to access data housed separately via APIs in real-time, giving SPS visibility into insurance claims and customer activity due to the disaster, enhancing the prediction algorithm.
If a customer called the insurance company or SPS, the response would be consistent.
This resulted in reduced timelines for customers to receive insurance settlements, which allowed them to get their lives back in order quickly after this devastating event.
SPS is using digital technologies to transform the mortgage servicing value chain fundamentally. It has transformed paper-based archaic processes to reduce cost and improve scalability while remaining 100% committed to unwavering compliance standards while significantly improving the customer experience.
Bringing operational efficiencies and ensuring compliance standards are met by reducing cost and time through digital document management is certainly not the purview of just the mortgage servicing industry. Techniques such as using ML-driven document classification to identify the right document types and versions, extracting relevant data from multiple document types using OCR and NLP can undoubtedly be applied to other industries.
Note: Moor Insights & Strategy writers and editors may have contributed to this article.
Moor Insights & Strategy, like all research and analyst firms, provides or has provided paid research, analysis, advising, or consulting to many high-tech companies in the industry, including 8×8, Advanced Micro Devices, Amazon, Applied Micro, ARM, Aruba Networks, AT&T, AWS, A-10 Strategies, Bitfusion, Blaize, Box, Broadcom, Calix, Cisco Systems, Clear Software, Cloudera, Clumio, Cognitive Systems, CompuCom, Dell, Dell EMC, Dell Technologies, Diablo Technologies, Digital Optics, Dreamchain, Echelon, Ericsson, Extreme Networks, Flex, Foxconn, Frame (now VMware), Fujitsu, Gen Z Consortium, Glue Networks, GlobalFoundries, Google (Nest-Revolve), Google Cloud, HP Inc., Hewlett Packard Enterprise, Honeywell, Huawei Technologies, IBM, Ion VR, Inseego, Infosys, Intel, Interdigital, Jabil Circuit, Konica Minolta, Lattice Semiconductor, Lenovo, Linux Foundation, MapBox, Marvell, Mavenir, Marseille Inc, Mayfair Equity, Meraki (Cisco), Mesophere, Microsoft, Mojo Networks, National Instruments, NetApp, Nightwatch, NOKIA (Alcatel-Lucent), Nortek, Novumind, NVIDIA, Nuvia, ON Semiconductor, ONUG, OpenStack Foundation, Oracle, Poly, Panasas, Peraso, Pexip, Pixelworks, Plume Design, Poly, Portworx, Pure Storage, Qualcomm, Rackspace, Rambus, Rayvolt E-Bikes, Red Hat, Residio, Samsung Electronics, SAP, SAS, Scale Computing, Schneider Electric, Silver Peak, SONY, Springpath, Spirent, Splunk, Sprint, Stratus Technologies, Symantec, Synaptics, Syniverse, Synopsys, Tanium, TE Connectivity, TensTorrent, Tobii Technology, T-Mobile, Twitter, Unity Technologies, UiPath, Verizon Communications, Vidyo, VMware, Wave Computing, Wellsmith, Xilinx, Zebra, Zededa, and Zoho which may be cited in blogs and research.