Chatbots could also play a major role in the discovery of investment ideas and curating financial information. A Siri in a chatbot form. A personalized chatbot for financial investments. These are the advantages of a chatbot:

  1. A natural language interface for the user: this creates the opportunity to service users without requiring them to “learn” your UX. It also gives users the possibility of making a very wide range of requests. Unfortunately, living up to the full promise of a chatbot in this regard requires very advanced language parsing logic, which in turn requires both pretty advanced AI, large sets of training data, and semantic knowledge as well (i.e., something to tell the system words to mean and how those concepts are related).

  2. A natural language interface for the service: a chat also happens to be a fantastic format for information that needs to be delivered in narrative forms, like explanations. The service can deliver information, and then the user can ask for clarification on specific elements. (Just like a real conversation!)

  3. Low threshold, near-native application access: no website to register for, no app to install, so users can access it immediately.

  4. Contextual knowledge about the user: the chatbot can know about the user’s transaction history, so the user can say things like “I want to dispute the credit card charge from yesterday.” The tricky thing here is all about getting the permissions for user data right. I’d be unpleasantly surprised if, say, a trading chatbot started scolding me for spending too much money on my credit card!

What it does

It is your friendly neighborhood chatbot! It gives you quick financial information, just type what you want and it searches for it using different APIs such as the Blackrock API. It also suggests the risk factor for investing in a certain stock and all through the familiar Facebook messenger. It is also capable of showing different stock visualizations, as per the user's need!

How we built it

The backend is build using Flask and Python, with Facebook Messenger as the interface for the chatbot. We use several apis, all of which are running on my local server. We perform NLP using Dialogflow from google cloud, which helps us to extract utterances and intents.

Challenges we ran into

Honestly, a ton of them. It was the first time any of us worked with chatbots or NLP, so manually training the NLP model felt more difficult than it should have. Apart from that I had a really hard time figuring out how to send a rich text message including image and text from my server to the app using webhooks.

Accomplishments that we're proud of

Working remotely from different timezones was especially challenging with some team members leaving us in the middle, but we managed to hack it out.

What we learned

What's next for Foliox

Built With

Share this project: