We are Montreal AI

One of the great outcomes of the AIFest event in Montréal last weekend was an increased sense of unity among the different parts of the AI ecosystem here. We are all working together to make AI a new industry in this city. 

To that end, we have created an open letter to the applicants for the AI Supercluster program in Montréal. This is a federal program to invest in AI. We want to work with government, industry and academia to make the ecosystem a success. 

The letter is at wearemtlai.org. Fuzzy.ai’s co-founders have signed as well as dozens of leaders in the community. We encourage participants big and small to make their voices heard. We can only do this if we work together. 

Fuzzy.ai Sponsoring AIFest 2017

We’re excited to be a sponsor of the inaugural AIFest, as part of Montreal Startupfest.

MONTRÉAL-JULY-12-2017-8

The event is happening this Saturday July 15, and is presented by MTLDATA in partnership with Fuzzy.aiElement AI, TandemLaunch, Nexalogy, Maluuba, Keatext and Mnubo.

AIFest will gather a group of 200 people interested in exploring and tackling the tough problems in Artificial Intelligence and overlapping domains.

AIFest is an unconference, in the spirit of BarCamp. It will be a participant-driven meeting. The attendees will suggest topics to define the event’s agenda. Anyone who wants to initiate a discussion on any topic related to AI can claim the time and space.

We can’t wait to participate in the event and hope to see you there!

For more information, visit the AIFest site.

Security issue in Fuzzy.ai API fixed

We’ve identified and corrected a content spoofing issue in the API server for Fuzzy.ai. Thanks to Nessim Jerbi for identifying and reporting this security bug, as well as recommending a fix.

Our 404 handler on the API server would echo the erroneous path in its error message. An attacker could craft a path that would inject text into the error message for other users, giving the impression that it was an official message from Fuzzy.ai.

We’re not aware of any abuse of this bug having occurred. The bug has been patched on our servers and does not require any updates to client software or SDKs.

Build Fraud Detection Into Your Apps

There are a number of fraud detection tools available on the market, but for some companies, it’s important to have greater control over how the fraud scoring algorithms work and to have them keep learning and improving using machine learning. Our team has put together a demo and some sample code to show how you can build this with Fuzzy.ai.

fraud score

For this example, let’s assume that Fuzzy.ai is being used by a company with an online store, where customers order products online. After running their business for a year, they’ve noticed that all of the following factors often indicate that a transaction is fraudulent:

  • Transactions from new users
  • Transactions much larger than the online store’s average size
  • Mismatches and very large distances between the billing address, shipping address, phone number location and IP address location

They also noticed that in addition to the points above, some lesser indicators of fraud are:

  • Using the most expensive shipping option might indicate fraud
  • Multiple credit cards used from same IP increases fraud
  • Multiple credit cards shipping to the same address increases fraud

Fraud_detection

With Fuzzy.ai, you could quickly build an agent based on these rules and get a fraud score in real-time for each transaction. In fact, we built one and created a demo interface you could use to try it out:

Visit our Fraud Detection demo site

We’ve also made all of the code behind this demo available. Check it out on GitHub.

Using a Chatbot to Offer Dynamic Promo Codes

Chatbots have become a really popular way for companies to interact with customers. Most chatbot experiences, though, are pretty static. As a developer, you need to set up a messaging flow with content that doesn’t change much based on user interaction.

Some of our users have discovered that you can use Fuzzy.ai along with most chatbot frameworks to create a much more personalized experience for your customers. Some examples include offering dynamic promotions based on user behavior, and recommending the most appropriate products.

To show this in action, we’ve built a sample bot that we call the Fuzzy.ai Promobot. You can chat with Promobot on Facebook Messenger and based on how you answer the questions it asks, Promobot will offer you a personalized discount on your Fuzzy.ai subscription. Promobot is built using Howdy.ai’s Botkit toolkit.

Here’s a sample chat with Promobot:

dynamic chatbot coupon.png

Behind the scenes, Fuzzy.ai is taking the data from the chat responses to predict the discount most likely to result in a purchase. To get started, the Fuzzy.ai agent powering the discount decision is a pretty simple one. It’s based on these 5 rules:

IF hasAccount IS no THEN discount IS high
IF hasAccount IS yes THEN discount IS low
IF tutorial IS no THEN discount IS high
IF tutorial IS yes THEN discount IS low
lastAPICall INCREASES discount

And the discount that Promobot offers in our example ranges from 0% to 20% based on the user’s responses.

Once Promobot offers the user a discount code, it then uses Fuzzy.ai’s machine learning to automatically optimize its rules to offer the lowest effective discount possible.

chatbot machine learning.png

In our example, Promobot does this by asking the user if they plan on using the discount code and then providing that feedback to Fuzzy.ai. In real implementations, you might send this feedback to Fuzzy.ai once the user actually makes a purchase.

The feedback Promobot provides is the % of full price paid by the customer. So, if Promobot offers a 15% discount and the customer says they plan to use it, Promobot sends “85” (100% minus 15%) to Fuzzy.ai. If the customer says they don’t plan to use it, then we consider it a lost sale and Promobot sends “0” (zero) to Fuzzy.ai.

Fuzzy.ai’s machine learning algorithms are seeking to maximize this value, and will automatically optimize the rules to get the highest possible result.

This is a simple example, but a more complex one could include dozens of questions and external data to create a truly personalized experience.

Please feel free to chat with Promobot on Facebook Messenger and check out the project’s code on GitHub to fork it for your own bots.