Avenga’s response to the war on Ukraine: Business Continuity and Humanitarian Aid
Extracted valuable data for informed business decisions
About the client
Our client is a leading global financial consulting company that supports financial advisors, consultants, and institutional investors.
The client, operating in the financial sector, is working with large collections of client meeting notes in order to search for certain information, then organize and consolidate it into easy-to-read interactive sets so it could be used for different business purposes. So, they needed to search, find, and process texts quickly, and obtain actual insights from the data across the notes, in order to understand their (potential) customers, identify market trends and risks for further informed business decisions by tagging documents with labels.
To enable fast searches through the text that would reveal actual valuable information, out-of-the-box and custom approaches were compared:
We offered to use Topic Modeling which helps to determine the list of topics discussed in an entire collection of meeting notes and that reveals the presence of one or more topics in each document. Also, our team used Named Entity Recognition for detecting a word or phrase in a text which has either a preset generic entity type (Location, Person, Geographical and Geopolitical entity) or a custom type (Product, Organization, financial entities).
Both approaches allowed for the retrieval of information from unstructured texts, overlaying the context on the content by tagging it with machine-readable metadata. However, the custom approach enabled the labeling of new and unseen documents on the fly, with one or more topics found as a result of a topic modeling algorithm.
This best suits cases where a finer control of the training, optimization, and hosting of a topic model is required (e.g. when we deal with specific texts’ domain, like in our case). Moreover, a custom model is tuned during development, so that it requires no additional effort. Using custom NER solutions, based on a deep learning model, we can detect both default and custom entities in real-time.
Our solution helps to automatically search through the raw unstructured text quickly, process it, and extract the actual data for informed business decisions. It enables to: