There is a huge Credit gap (+3 T USD) in SMEs financing and traditional lenders are losing market share against Fintech because they are highly autocratic, considerably slow and offer bad conditions. It is very hard to get trustable information on SMEs (brick and mortars in this use case) to feed into traditional credit scoring models. This causes banks to lend working capital loans in a very sectorial manner, without any offer personalisation, no matter the performance of the borrower.
Synapse Scoring assesses the credit scoring of offline retailers analysing performance data only. Several retailers’ cash flow data (gathered through PSD2 API) and customer flow data (gathered through IoT devices installed inside the store) are modelled in order to define the set of probabilities of default at different maturities. Moreover, to induce the store manager to better manage the store and outperform, Synapse tool also includes a customer behaviour dashboard with comprehensive analytics over the in-store customer footfall.
In the first step of our journey into the product, we focused on the vision. This is where we got to know the problem head-to-toe and created a comprehensive brief for the project. It allowed us to gather all the research needed from the different stakeholders at the table. This prevented us from being blocked by a lack of information during the following phases.
After an immersive session with all the stakeholders, we had all the information we needed to create the ultimate list of User Stories and features necessary to prove the main assumptions in a Proof of Concept (POC). Our experts in Product, UX/UI and Tech Architecture focused on finding the answers to all of the questions raised throughout the scope preparation. On the tech side we elaborated a memorandum tackling our suggested approaches for tech stack selection, database technology and orchestration. Together with Bocconi University and AlixPartners we started defining the useful datasets and the algorithm behind the lending decisions. Together with Bocconi University and AlixPartners we started defining the algorithm behind the lending decisions.
We programmed and assembled the IoTs ourselves, and installed them in key stores to fine tune the monitoring parameters. Meanwhile, the data team started gathering data from the IoTs and testing the algorithm parameters.
We developed a non-functional prototype to simulate users’ interactions (for both the dashboard for the store manager and the one for the banker). The experience of using the clickable prototype was very much like the final product itself, this was the adequate phase to test the information architecture, the UX and most importantly to present all involved counterparts a concrete outcome.
With the decisions closed in the previous steps, we went on developing the tool through agile cycles.
By knowing what’s happening inside the store (both financially and behaviour-wise) in real-time, the financial institution can pre-approve lines of credit personalised for each of the retailers, that can be instantaneously withdrawn with one click by the store manager.
Through the IoT devices installation in key positions around the store (at least close to the store window, inside the store - on different shelves - and close to the cash machine) and triangulation of customer footfall data, the system is able to recreate an offline conversion funnel.
Tool to help bankers aggregate retailers portfolios as they may like; no restriction on any variable (e.g. Fashion retailers, -1M EUR Turnover, with store in Milan).
Real estate in a decision-making dashboard is always a great UX challenge, on one side the user wants to have access to all information, on the other hand, too much information struggling for user's attention defeats the purpose of a clear BI dshboard. We came up with the expandable panel concept, where each key metric starts with a point in time current position and when needed, the user can expand the metric to see it's time evolution and also the comparison with the homologous period.