Design Sprint

Confused after leaving the subway? New concept feature that improves urban navigation designed in just 5 days!

Imagine you have been underground for a while. You come out of the public transit to find yourself surrounded by unfamiliar buildings, a densely packed crowd walking in all directions speaking in a foreign language, and cars honking. You feel like you are standing out and decide to take a left. After walking for a few minutes, you realize you are going in the opposite direction.

Image for post
Image for post
Source: Maël BALLAND

As someone with no sense of directions, moving to and getting around in Brazil and Germany as an international student wouldn’t have been possible without Google Maps. However, navigating in big cities like São…


NLP in Finance

Tutorial on how to build a production-ready Financial QA system

Image for post
Image for post
(Image by the author)

Part 1 — Learn how to use the neural search framework, Jina, to build a Financial Question Answering (QA) search application with the FiQA dataset, PyTorch, and Hugging Face transformers.

Part 2 — Learn how evaluate and improve your Financial QA search results with Jina

For my master’s thesis, I built a Financial QA system using a fine-tuned BERT model called FinBERT-QA. Motivated by the emerging demand in the financial industry for the automatic analysis of unstructured and structured data at scale, QA systems can provide lucrative and competitive advantages to companies by facilitating the decision making of financial advisers.


Geospatial Analytics

Vision: Using data to enable marketers to determine where to place their advertisements

Client: Intermx
Team: 1 Designer (Me), 1 Product Design Lead
My Role: Ideation, UI Design, Prototyping
Duration: 2 days
Tool: Figma

Image for post
Image for post
Final Prototype (GIF by the author)

Overview

Problem: An advertising company wants to find out how people of Columbus, Ohio have been moving around from January 2019 to January 2021 across its neighborhoods.

Understanding the data behind how people move and the demographics of these people can provide actionable insights to advertising companies. …


NLP in Finance

Tutorial on how evaluate and improve your Financial QA search results with Jina

Image for post
Image for post
(Image by the author)

Part 1 — Learn how to use the neural search framework, Jina, to build a Financial Question Answering (QA) search application with the FiQA dataset, PyTorch, and Hugging Face transformers.

Part 2 — Learn how evaluate and improve your Financial QA search results with Jina

In the previous tutorial we learned how to build a production-ready Financial Question Answering search application with Jina and BERT. In order to improve our application and retrieve meaningful answers, evaluating the search results is essential for tuning the parameters of the system. …

Bithiah Yuan

Feel free to connect with me on Linkedin! https://www.linkedin.com/in/yuanb

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store