About the Company
Founded in 2022 with offices in London, Singapore, and Mumbai, Kelp is a FinTech solution that uniquely combines predictive technology with comprehensive private company data to support alternative investments from inception to exit. The platform offers an end-to-end product with three core modules: Deal Identification, Deal Management, and Value Creation. Fully modular, Kelp enhances organizational intelligence and automates routine tasks for efficient decision-making. Its prescriptive decision engine empowers investment professionals with transformed data, provides actionable insights, and streamlines workflows for effectiveness and continuous learning.
Partnership with Tailored AI
Kelp entered into a long term partnership with Tailored AI to enhance their product offerings after rigorous evaluation. Tailored AI engages with Kelp on tasks that involve building LLM powered Products that perform Text Analytics (Classification and Summarization) and Text Extraction from large unstructured datasets. Tailored AI also builds Model Evaluation pipelines that allow Kelp to test and iterate rapidly on existing models when newer, better models are out in the market. Some Problem Statements that Tailored AI has worked on are mentioned below.
Problem Statement 1
The customer had a proprietary database of 2M+ Employee reviews . Out of these, only a few reviews provide investor-critical data like misdoings or bias within the company. It would have taken 22000+ man hours to manually identify each critical review, and classify it correctly.
Key Challenges
The employees can potentially be talking about endless workplace topics in their review. Using a regular classification algorithm on these with high accuracy is close to impossible. On the other hand, LLMs offer high accuracy if we group topics and bring down the number of classes to ~20, but are extremely costly. Hence, data cannot be fed into an LLM blindly, and must undergo processing and compression to get high accuracy in a cost effective manner.
Solution Approach
We explored several algorithms to identify data-backed critical reviews, including KNN with BERT embeddings, automated topic generation using topicGPT, sentence embeddings with Open AI, etc. However, none of these could handle the large number of classes and classify reviews with high accuracy.
We then explored using GPT 4 along with prompt engineering, and were satisfied with the accuracy. However, there was a concern regarding the cost and latency. We tackled this using automated data cleaning, and disregarding data where there is less likelihood of finding critical reviews. This helped bring down costs to a manageable level. Additionally, the costs would continue to reduce with newer, cheaper, and faster LLMs by simply swapping the model after evaluating results on the test data set.
Problem Statement 2
Business Analysts and Market Analysts spend hours extracting Investor critical information from News Articles, Market Reports, Financial Reports, etc. Along with cost, this also adds to the Turnaround time that is highly sensitive when it comes to investments.
Solution Approach
Tailored AI used a combination of Prompt Tuning and Post Processing the Model output to achieve the required results. The details of the methodology are confidential.
