How will Chatbots be used in Wealth management?

Chatbots in Wealth managment are at a very early stage. In this post I cover the current use cases.

How will Chatbots be used for wealth management? Any cases that you are aware of, you can add below:

  1. For basic portfolio information and updates (positions, cash, risk units, industry exposures, correlations to existing holdings etc.); like myKaI.

  2. For executing trades or other transactions; like AJBellYouth.

  3. Chatbots could also play a major role in discovery of investment ideas and curating financial information. A Siri in a chatbot form. A personalized chatbot for financial investments, much like what PollyChat is trying.

  4. Will Chatbots be a way that robo-advisors effectively and cheaply stay in touch with clients and personalize their profiles and asset allocation?

  5. Will brokers adapt chatbots as the best customer engagement portal with a combination of Machine learning and artificial intelligence?


First time poster here, and in full disclosure, CEO of Polly Portfolio.

I think Efi has outlined the major potential applications, but it’s also useful to touch on why chatbots are important, i.e., why are chatbots going to be used for these applications? People talk about chatbots like they’re a unified phenomenon, but in reality, they’re at least four different things:

  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 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 form, 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 permissioning 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!

Transactional applications (executing trades like AJBellYouth or our friends at and reporting applications (like myKal) primarily rely on facets #3 and 4.

Marketing applications primarily rely on facets #3 and maybe 1 and 2.

Engagement applications rely on facets #2, 3, and 4.

And customer service applications end up relying on all four facets.

I would say that our chatbot is essentially an engagement application that gradually builds up knowledge about the customer to better surface customized investment ideas. We explicitly decided to rely almost entirely on structured interfaces for our application because we didn’t think the technology was ready for allowing natural language requests from the user (and in our case, that wasn’t critical to a good user experience).

I’m curious as to what others think the limitations are on the expansion of chatbot applications.


I would think that the current state of knowledge in a particular field will be a limitation.

Great points @jasen and @Efi.

I’m somehow not convinced if chatbots are here to stay. In India (where I’m based),there are always people available to reply to questions, as its cheaper than the automation. I’d guess this would be true in several other countries. (Most other emerging markets). From personal experience, the GUI provides a better interface than the chat/call as you have to learn the UI only the first time. Your portfolio value/prices/ order status etc is visible at a glance without having to request it specifically.

The case where I prefer talking to the broker is when I want to discuss their view on a particular stock or two, and that seems a bit hard for a bot, especially one that uses natural language processing than a guided flow of questions.

There is also some delay between asking questions, reading the response and choosing, while UIs are static and with familiarity, takes only a couple of seconds for most tasks.

Of the points above, I think point 4. Stay in touch with clients cheaply might be the best fit for chatbots. When the bots get good enough to handle even complex questions, thats when it’ll get really interesting.


1 Like

Jasen, Good comments bots are designed by humans. It is not a more advanced species. It’s not even a general intelligence, (big) possible when AI 2 AI algos are in the game we might see changes.

1 Like

Please don’t forget the compliance risk with the implementation in WM. Any automatic programed response is potentially still investment advice!
I believe that IBM id at the forefront of that technology to used behavior and past data to create meaningful response. The US gov for other reasons as well. …

1 Like