New Articles
  July 3rd, 2018 | Written by

Machine Learning Critical for Better SME Credit Scoring in Trade Finance

[shareaholic app="share_buttons" id="13106399"]


  • Whitepaper argues AI credit-scoring can dramatically improve SME access to trade finance.
  • Key problem exacerbating $1.5 trillion trade finance gap: the lack of available credit to SMEs.
  • Inadequate credit-scoring by banks and other lenders leads to trade finance gap.

Tradeteq, the trade asset distribution platform, has today released a white paper aimed at demonstrating how machine learning, combined with broader data collection, can improve access to trade finance for SMEs. Authored by Michael Boguslavsky, Tradeteq’s head of AI, and titled Machine Learning Credit Analytics for Trade Finance, the paper proposes a radical new approach to credit scoring that could particularly benefit SMEs in trade finance.

The paper states that traditional models – such as the Altman Z-score – use a “linear discriminant” analysis, which is based on several accounting indicators. While widely utilised, such scoring presents a number of issues for SMEs – including focusing on a small number of accounting entries while ignoring valuable non-accounting information. Such hard requirements make credit scoring impossible for companies that miss even one entry. Being based on accounting data filed on an annual basis, traditional scoring also lacks timely information.

“Over the years there have been many attempts to improve traditional credit scoring,” said Michael Boguslavsky, “such as adding new financial ratios or replacing the Altman Z linear approach with other models. But they have never been very successful. What’s needed are models able to leverage non-homogeneous data from multiple data sources – dramatically improving both quality and timeliness of credit event prediction.”

Boguslavsky’s white paper argues that a good predictive credit model for trade finance lending should: accommodate varying data availability across companies to increase the depth of datasets; leverage a broad set of available and emerging data sources, including geographical data; and utilize trade network data, including common clients, suppliers, or bank relationships, to spot irregularities and predict credit risk.

It’s this approach that will allow for a broader understanding of SMEs’ credit risk, leading to fewer loan rejections and improved credit decisions, claimed Boguslavsky.

“The combination of machine learning techniques with deep and broad data coverage generates a neural network model that can outperform the traditional Altman Z-score and similar models even on pure registration data,” he said . “And this without using any accounting inputs – hence it’s potentially revolutionary impact on SMEs seeking trade finance.”

Tradeteq’s trade asset distribution platform generates credit scoring in just such a way, with the aim of expanding the universe of trade finance investors by encouraging an “originate to distribute” model by trade finance banks. The company – officially launched in March 2018 – is now looking for partnerships and collaborations to work on transaction-level trade finance datasets, leveraging Tradeteq’s expertise in deep data analysis and the broad data sourced from partners to produce state-of-the-art credit analysis for the trade finance community.