AI-Powered Financial Analysis and Recommendation System

Features

• Investment portfolio analysis and optimization
• Fund recommendation based on quantitative analysis and backtesting
• Client prioritization – determines which clients to call first and why, based on clients’ portfolios, transactions, CRM notes, and analyses of market events
• Content recommendations – recommends news and research papers relevant to a client’s business and current market situation
• Chatbot with natural language interface – possesses ability to answer advanced questions about specific funds, stocks, or market events
• Real-time analysis of multiple data feeds from Thomson Reuters, Morningstar, and other sources

How it Started

June 2015

The client contacted Itexus via a referral from a previous client with an idea for a FinTech product. Initially, the functionality of the system was very small: it was meant to provide quantitative recommendations of liquid alternatives (mainly Hedge Funds) for client portfolios by analyzing mutual correlations, risk/return ratios, etc.

Discovery Phase

July 2015

We started the project with a discovery phase, during which the Itexus team translated the client’s idea into a requirements specification. Our Software Architect analyzed suggested integrations and came up with an estimate and architecture for the MVP of the system.

First Version

October 2015

The initial MVP allowed a user to upload their portfolio, show quantitative analysis of the portfolio, and receive a recommendation for its optimization using pre-configured securities.

It had two integrations:

• Xignite — to obtain daily price changes for a variety of securities from NYSE and NASDAQ;
• Raise Partner – a quantitative analysis engine that calculated various financial metrics (e.g., Risk, Return, Sharpe Ratio, Skewness, Max Drawdown, Diversification, and Volatility) of the portfolio, including the portfolio as a whole as well as the contributions of each instrument in the portfolio. This also allowed portfolio optimization to achieve various goals (e.g., minimize risk, maximize return).

Change of the Strategy

January 2016 – Summer 2017

The client’s vision for an AI-based system able to answer any financial question and provide users with personalized content ended up being too big to implement in such a short time frame and with the seed round investment budget.

The product was also arguably too big to sell, as it envisioned a significant reimagining of the way financial institutions work. Meanwhile, seed round money began to run out over time. Eventually, development was put on pause as the Client took time to rethink their strategy.

AI Content Recommendation and Client Prioritization System

August 2017

After a few months’ pause, the Client came back to us with a new product strategy. He decided to narrow the focus in the near term, instead aiming to start build incrementally with smaller, more practical steps. This meant starting with intelligent APIs that could supplement existing processes and systems used in the financial world, rather than aiming to replace them. This also meant that each API could be sold separately.

The first version of this new product contained two APIs:

• Content personalization
• Client prioritization

With the help of various machine learning algorithms, the APIs analyze all the information financial institutions have on their clients: CRM data and notes, recent transactions, portfolios, market information in the news about their sector/location, etc.

This solution could also be used to improve the efficiency of client relationship managers. The system recommends which clients should be called first, as it indicates if there may be a problem that needs to be solved or if there is an opportunity for cross-selling. Managers could also utilize the system to be better prepared for meetings by reading relevant content (e.g., news, bank’s analytical material, about products, industry, and trends) about a given client through the platform .

The content personalization API analyzes real-time data feeds and processes them with various NLP techniques. With the help of machine learning algorithms, it recommends which content is most relevant to a given client, thus saving time spent on manual preparation while still providing a service that is much more personalized to individual end clients.

First Real Clients

April 2018 – May 2018

A large European commercial bank and a U.S. asset management company became the first clients of the AI-powered platform. In May 2018, the client successfully secured Series A investment funding of $5 000 000 from a strategic investor.

Present Day

The project is ongoing to this day, with a focus on new client acquisition and the addition of increasingly more  AI and financial functionality to the product.