Company

System: A utility to accurately extract financial information from company financial statements in arbitrary format. Specific details are subject to NDA.

Client: Protected by NDA

Technologies: Raku, Python

Problem: The arbitrary format of company financial statements presents a problem for automated analysis

Solution: Our solution takes advantage of the standard accounting terms classification system as well as known financial mathematical relationships to produce output above a certain desired accuracy threshold. Specific details are NDA protected.

System:  Specific details are protected by NDA. However, this system - developed over a number of years - involved creation of a unique architecture utilising LLM technology in a novel way. 

Client: NDA Protected

Technologies: Llama3-70B (and other LLM and ML models), vLLM, Python, Transformers, Algorithms

Problem: NDA Protected - but relates to asset price prediction

Solution: The innovative approach involved making an analogy between the "fuzzy" system we needed to model, and certain more rigorously defined mathematical/physical systems. Specific details are NDA protected. For the implementation we took advantage of per-hour cloud GPU rental to perform the necessary heavy processing as cost-efficiently as possible. 

System: "SuperGraph" Native Android App

Client: John Adams Ltd.

Technologies: Java, Android, XML

Problem: The app had been removed from the Google Play Store due to a reported stability issue. There were also problems with accessibility of some buttons on smaller screens.

Solution: Several minor fixes were implemented including build parameter and file format updates, and layouts were corrected to make missing buttons visible on smaller screens. Updates were tested on multiple emulators using Android Studio. The app was successfully redeployed to the Google Play Store, and a report produced detailing the changes.

Before:

After: