Xceptor Lasers in on ML and NLP 

Data ingestion and process automation provider Xceptor is building out the machine-learning (ML) and natural-language processing (NLP) functionalities of its platform.

The no-code platform has native artificial intelligence (AI), workflow, reconciliation, and exception management for end-to-end automation. 

Andrew Kouloumbrides, CEO of the London-based software vendor, says that typically a data scientist would configure the AI functionality in the platform. However, with Xceptor, the configuration is done by the end user. Much of the existing ML functionality is for data enrichment and capture. 

Xceptor can consume simple, structured and unstructured data. As more firms begin to automate an increasing amount of unstructured data, Xceptor uses NLP to read and route email instructions from clients to identify clauses in complex contracts. 

Xceptor will consider including deep learning capabilities, Kouloumbrides says. And the depth and breadth of its data ingestion functionality are becoming more important as firms look to extract value from derived, unstructured data, and alternative data. 

Deutsche Bank recently onboarded Xceptor’s platform to automate its core operational processes in Indonesia. Xceptor will help the bank automate reconciliations with multiple external parties for its securities services business. For example, the platform will be used to automate the computation of components of taxes such as capital gains and withholdings. 

Jeslyn Tan, global head of product management, securities services at Deutsche Bank, says: “We will look into deploying Xceptor’s solution in other locations once it has been implemented successfully in Indonesia.” 

In December 2018, the Depository Trust and Clearing Corp. integrated Xceptor’s software to assist with reports submitted to trade repositories for the Securities Financing Transactions Regulation. 

Using Xceptor’s platform, DTCC clients can capture and normalize data in any format. The service also provides a pre-check review for data enrichment and validation, allowing firms to make corrections to the data before submitting to a trade repository.