October 10, 2017 By Manu Karnam 3 min read

How to build an investment management chatbot

Chatbots, as a means of customer interaction, are taking the financial sphere by storm as more bots are launched weekly.  Established financial institutions, mostly in the retail-banking sector, investment management and wealth management sectors, are jumping on the bandwagon and experimenting with bots. Financial institutions have embraced this trend and experts predict that, within five years, bots will replace conventional online interfaces such as websites or mobile apps.

To give you a head start, we’ve built a starter kit to help you better serve your clients (something that digs a layer deeper than just saying innovation) The Watson Conversation based Wealth Management Chatbot starter kit enables you to query your investments, to analyze the effect of various scenarios on them, and to switch between a web interface and a Twilio interface.

Start building with the starter kit today. We’ve selected and configured the essential components so you can get your hands on the code right away. You’ll be setup with the following services:

Once you deploy, check out the recommended next steps to build on the starter kit. For example, you can build support for additional market scenarios or add the Twilio interface. Here’s an example architecture and details on how the code works:

  1. Set up multiple communication channels (for example, WebUI or Twilio). The application listens for messages from either channel.

  2. The Conversation API takes in natural language input and breaks and maps it to intents and entities that it has been trained for. The app makes a call to the respective financial service based on the intent that was identified. Train Conversation for additional intents and entities to make for a more robust conversation experience.

  3. The context of the conversation is saved to Cloudant DB so that the Conversation API is able to save the state and track the conversation flow of the user.

  4. The Portfolio Investment API is called if there is a query asking for information around the holdings or portfolio. An asynchronous call is made through a “Promise Request” to make the query and return the results. Subsequently, the results are parsed and formatted in a response object that is sent back to the Conversation interface.

  5. The Simulated Analytics API is called if the intent is identified as “impact analysis.” This call initially requires issuing an asynchronous “Promise Request” querying the name of the holdings currently owned using the Portfolio Investment API. This is stored in an object that is subsequently sent to the Simulated Instrument Analytics service (SIA). SIA pulls the base and conditional price out of the object in order to compare against the potential market changes and return a measure of the impact to the holdings in this scenario. (In this use case, the change scenario is querying how the portfolio would perform if the S&P 500 drops by 5%. Results are parsed and formatted in a response object that is sent back to the Conversation interface.

Get the kit and start building your wealth management chatbot on Bluemix today and get a 15-day trial of on-demand consulting, ask us anything!

More from

AI in commerce: Essential use cases for B2B and B2C

9 min read - Four AI in commerce use cases are already transforming the customer journey: modernization and business model expansion; dynamic product experience management (PXM); order intelligence; and payments and security.  By implementing effective solutions for AI in commerce, brands can create seamless, personalized buying experiences that increase customer loyalty, customer engagement, retention and share of wallet across B2B and B2C channels.  Poorly run implementations of traditional or generative AI in commerce—such as models trained on inadequate or inappropriate data—lead to bad experiences…

A new era in BI: Overcoming low adoption to make smart decisions accessible for all

5 min read - Organizations today are both empowered and overwhelmed by data. This paradox lies at the heart of modern business strategy: while there's an unprecedented amount of data available, unlocking actionable insights requires more than access to numbers. The push to enhance productivity, use resources wisely, and boost sustainability through data-driven decision-making is stronger than ever. Yet, the low adoption rates of business intelligence (BI) tools present a significant hurdle. According to Gartner, although the number of employees that use analytics and…

Achieving cloud excellence and efficiency with cloud maturity models

6 min read - Business leaders worldwide are asking their teams the same question: “Are we using the cloud effectively?” This quandary often comes with an accompanying worry: “Are we spending too much money on cloud computing?” Given the statistics—82% of surveyed respondents in a 2023 Statista study cited managing cloud spend as a significant challenge—it’s a legitimate concern. Concerns around security, governance and lack of resources and expertise also top the list of respondents’ concerns. Cloud maturity models are a useful tool for…

IBM Newsletters

Get our newsletters and topic updates that deliver the latest thought leadership and insights on emerging trends.
Subscribe now More newsletters