The solution is now live in key markets across Asia, Africa, and the Middle East1, with more markets across the bank’s footprint to follow, according to a media release. Traditional documentary trade requires millions of data elements in paper-based, unstructured documents – often issued by various companies – to be reviewed through a largely manual process.
With the implementation of Standard Chartered’s Trade AI Engine powered by IBM, this time-consuming and high-risk process is now significantly automated:
- Conversion of non-digital shipping documents into machine-readable format enabled by Optical Character Recognition (OCR)
- Identification and classification of document types from an initial pre-defined database
- Continuous Machine learning (ML) based on user re-classification/re-defining of data elements to further improve accuracy
- Natural Language Processing (NLP) capabilities to read and capture context from data in the documents
The innovative solution allows the ban to handle high volumes of diverse back office tasks with greater efficiency and accuracy, thus offering a more seamless trade processing experience for clients.
The «Trade AI Engine» is currently live in India, Nepal, Botswana, Kenya, Uganda, South Africa, Zambia, Tanzania, Zimbabwe, Angola, Cameroon, Côte d’Ivoire, Gambia, Ghana, Nigeria, Sierra Leone, Mauritius, UAE, U.K., Iraq, Bangladesh, Thailand, Philippines, Indonesia, Pakistan, Sri Lanka, Bahrain, Qatar, Jordan and Oman.
Additional markets to follow are Japan, Brunei, Indonesia, Taiwan, Hong Kong, Singapore, Malaysia, China, and the U.S.