Skip to main content

Engineering

Discussions around machine learning, artificial intelligence, and fintech development

  • 3 Topics
  • 1 Reply
3 Topics
edsolovey
edsoloveyDigits Team
published in Engineering
Efficient Serving of Static Views with Google Cloud Spannerliving model

 At Digits, we strive to push the bounds of technology in order to deliver radically more useful, delightful software experiences for our customers. We’re excited to begin sharing a closer look at the technical foundations that underpin our products in a new series of blog posts called Building Digits. Without further ado…Let’s talk about viewing complex data. One of our primary goals at Digits is to provide business owners with insightful and holistic views of their company’s finances, in substantially real-time. Achieving this involves three major, independent steps: We collect all of their relevant data from various sources, such as their QuickBooks, the financial institutions they bank with, their corporate credit card providers, etc. We apply our algorithms and proprietary datasets to extend, interpret, and tease out meaning from all of their data. We consolidate and aggregate the results into a holistic view that we then visualize for them on their dashboard.FactsWe refer to the

2280
edsolovey
2 years ago
Brian
BrianDigits Team
published in Engineering
Architecting Digits Search: Real-time Transaction Indexing With BleveDigits Search

We launched Digits Search, which brings fast, beautiful, full-depth search to business financial data. We’ve received a ton of great customer feedback, but one question just keeps coming up…How did you build this!?Well, let’s break down how Digits Search puts your finances at your fingertips.Digits ArchitectureFirst, some quick background on Digits:Digits links with your business’ accounting software and your financial institutions to build, and continually maintain, a living model of your business with the most up-to-date data. Once linked, we ingest all of that financial data in raw form, a collection that we call “facts”. We then use machine learning and data processing to normalize all of that overlapping, unstructured data. We perform a significant number of calculations to fill holes in the picture, such as predicting how your latest transactions will be categorized, detecting and predicting recurring activity, etc.The end result of all this work is a “view”, which is then effici

5560
Brian
2 years ago
hannes
hannesDigits Team
published in Engineering
Training and Deploying State of the Art Transformer Models at Digitsliving model

Understanding banking transactions as they happen, in real-time, is core to our mission with Digits Search. You can’t answer important finance questions with bad data.Transaction descriptions contain valuable information which helps us understand and communicate our customers’ business activity. The information we extract is then indexed and made available via Digits Search, and presented in a far more human-readable and intuitive manner than they would get from reviewing their raw bank or credit card statements.Here we wanted to share a peek behind the curtains on how we extract transaction information with Natural Language Processing (NLP) at Digits. You’ll learn how we apply state-of-the-art Transformer models to this problem and how we go from an ML model idea all the way to a production integration with our Digits Search product.Our PlanInformation can be extracted from unstructured text through a process called Named Entity Recognition (NER). This NLP concept has been around for

1820
hannes
2 years ago

Badge winners

Show all badges
Terms & ConditionsCookie settings