Abstract: Techniques for training a classification model to improve the classification of open banking transactions are presented. The techniques include receiving raw training data from a data source. The raw training data includes historical transaction data made up of a plurality of individual transactions. The raw training data is input into the classification model. The raw training data is processed by performing a data preparation operation on the raw training data. The data preparation operation includes removing numerical characters, repeating special characters, and accent words from the textual data of each transaction. Vocabulary training is then performed on the processed training data, including tokenizing the text of each transaction and converting the tokenized text into a transformer model specific format. The classification model is then trained using a transformer model, which uses the tokenized text. The trained classification model is then stored in a database.

Abstract: Techniques for training an entity resolution model are presented. The techniques include receiving a minimum viable data product (MVDP) scope, a product scope, and a data mining scope from a user. A data mining goal is determined based on the MVDP scope, product scope, and data mining scope. One or more proof of concept (PoC) models are defined based on the data mining goal, and one of the PoC models is selected for training. A trained deep learning model is generated by iteratively training the selected PoC model. The trained deep learning model is then tested and validated against a predefined achievable loss metric using a sample labelled dataset for testing.

Abstract: Techniques for training an entity resolution model are presented. The techniques include inputting raw training data into the entity resolution model. The training data includes historical transaction data including a plurality of transactions. A label dictionary is generated by performing natural language processing (NLP) on the training data. The NLP includes scanning text of each transaction, extracting one or more entities from the text, and storing the label dictionary in a database. The label dictionary includes the extracted entities. Tagged data is generated from the training data using the label dictionary. Vocabulary training is performed on the training data, including tokenizing the text of each transaction and converting the tokenized text into a transformer model specific format. The entity resolution model is then trained using a transformer model, which uses the tokenized text and the tagged data. The trained entity resolution model is then stored in a database.