Services Rendered
Product Design
Product Engineering
.svg)
Continuing Design
Our FinTech client wanted to increase the speed of collections with an accounts receivable platform that automates and provides incredible efficiencies for collection teams. To address this problem, Zemoso developed Textractive, an artificial intelligence (AI) and natural language processing (NLP) solution.
By 2025, McKinsey Global Institute predicts that data will be embedded in every decision, interaction, and process. As organizations become increasingly data-driven, they'll collect, analyze, and report on not only numbers but also text and images. Cue ChatGPT and Large Language Models. The world recently woke up to the fact that gaining valuable insights from the qualitative aspects of customer interactions is as essential for growth as it is from quantitative aspects of engagement. And learning models can do that for you: you just need to have enough data to train them and give them the right cues to track. Manual note-taking and interpretation is time-consuming, subjective, and can ignore vital cues. This problem becomes even more complex when there are thousands of interactions with different speech and cultural cues to analyze.
Collection agents handle hundreds, and sometimes thousands, of daily interactions and generate millions of records. It is challenging to track commitments, amounts, and other critical customer data from verbal exchanges. To address this problem, we built a solution that:
.svg)
Our clients love what we do:
We built a conversational intelligence solution to help collection agents make calls, take notes, and schedule follow up calls. Textractive, Zemoso’s proprietary conversational AI assistant, integrates with the autonomous receivables systems and assists collection call agents with their day-to-day tasks. It summarizes the conversation between collection agents and the customer, minimizes errors, and boosts productivity. It currently processes inputs in English, French, Spanish, German, and Russian.
Our engineering pod’s first challenge was to determine the best-suited tech stack to train and deliver this product on a fast-track timeline without losing accuracy. Here’s how we made it possible:
To ensure secure access to Textractive, we incorporated API key authentication as the first step in our workflow, authenticating agent IDs. Our Application Programming Interface (API) server, built using Python and Flask, performs the ID validation, authentication, and data pipeline functions.
We chose Rasa, the open-source conversational AI platform, to define pipelines for entities and intents, allowing us to customize our data pipelines to meet our clients' unique needs. Rasa's plug-in-based architecture seamlessly integrated with our overall product architecture, making it our top choice. Additionally, Rasa's flexibility allowed us to swap out ML models as needed, from BERT to Open AI GPT-3.
Zemoso analyzed some client-customer conversations to identify the major categories of intent, entities involved, and the amount of the transaction. They then classified and labeled the collected samples, and generated more sample conversations for different types of intents based on the results. Using these samples, Zemoso trained a Machine Learning (ML) model.
We utilized Google's Universal Sentence Encoder to encode text into high-dimensional vectors that could be classified based on intent or greetings. As a pre-trained ML model, it required less training and offered high accuracy. It enabled us to establish context by deciphering the meaning of ambiguous language in text and accelerated our go-to-market strategy.
We employed a Deep Neural Network (DNN) from TensorFlow for classification. TensorFlow is an end-to-end open-source library for Machine Learning (ML), widely used in the Google community.
We used various techniques such as regular expressions, rules engine, and ML methods like Conditional Random Fields (CRF) that take context into account. We used Meta’s high scale Duckling library to detect and extract entities like time, ordinals, dates, numbers, and currency.
Textractive's integration with the client’s platform has been a success. We leveraged our expertise in machine learning, deep neural networks, and natural language processing to deliver a solution that provided them with a significant competitive advantage in the market.
This FinTech unicorn has been able to process vast amounts of unstructured conversational data with Textractive with speed and accuracy. This kind of streamlining and amplification is significantly innovative for product companies that enable, automate, and optimize for service providers.
©2025 Zemoso Technologies. All rights reserved.
