utside of a doctor’s office, it doesn’t get much more personal than one’s wallet, so the idea of using Artificial Intelligence (AI) to manage investments is both exciting and a nail-biter. The regulatory concerns are significant, particularly when it comes to privacy, but AI’s ability to analyze data in novel ways, as well as perform mind-numbing repetitive tasks with unwavering enthusiasm, gives it enormous potential to improve financial services by both reducing costs and improving performance.
We will look at how AI is being used today by financial services firms and how individual investors can harness its power for their own portfolios.
AI in Financial Services Today
Generative AI refers to artificial intelligence technologies and applications that generate entirely new content including text (e.g. ChatGPT), audio (e.g. Resemble AI), images (e.g. Dall-E), video (e.g. Synthesia), code (e.g. GitHub Copilot) and data (e.g. Gretel Synthetics). Generative AI is already being used in the financial services industry and will be impacting how investors invest and interact with advisors.
While some financial services institutions, such as Bank of American (BAC), JP Morgan (JPM), Citigroup (C), Goldman Sachs (GS) and Wells Fargo (WFC) are restricting their employees’ use of OpenAI’s ChatGPT, others are embracing it. Morgan Stanley (MS) is using a chatbot powered by OpenAI to help its financial advisors better utilize the organization’s enormous repository of research and data. Last month, Ken Griffin, the founder of Citadel Securities, said his firms were in the process of negotiating an enterprise-wide license to use OpenAI’s ChatGPT tool to do everything from, “helping our developers write better code to translation software between languages to analyze various types of information that we analyze in the ordinary course of our business.”
Bloomberg recently released a research paper that covers the development of BloombergGPTTM, a new large-scale generative AI model that, “has been specifically trained on a wide range of financial data to support a diverse set of natural language processing (NLP) tasks within the financial industry.” The intent of the model is to, “assist Bloomberg in improving existing financial NLP tasks, such as sentiment analysis, named entity recognition, news classification, and question answering, among others.” While the attention on AI has exploded since OpenAI’s launch of ChatGPT late last year, AI has been used in financial services for years. For example, back in early 2021 HSBC (HSBC) launched Sympricot, an AI-based chatbot to give clients instant pricing and analytics for foreign exchange (FX) options.
AI for Better Returns
Why not start by asking ChatGPT?
Q: How can AI improve investment returns?
A: AI can improve investment returns in multiple ways. Here are some of them:
- Identifying Patterns: AI can analyze large volumes of data quickly to identify patterns in the financial markets. This can help investors make more informed decisions when it comes to investing in stocks, bonds, and other financial instruments.
- Risk Management: AI can help investors manage risk by monitoring market trends and identifying potential risks before they become problematic. This can help investors avoid losses and maximize their returns.
- Portfolio Optimization: AI can help investors optimize their portfolios by analyzing data on different investments and offering suggestions for diversification. This can improve returns by reducing the overall risk of the portfolio.
- Speed and Efficiency: AI can analyze data much faster than humans, allowing for quicker and more accurate investment decisions. This can help investors take advantage of opportunities as they arise and make trades more efficiently.
Overall, the use of AI in investment management can lead to more informed, efficient, and successful investment decisions, ultimately resulting in improved returns.
To expand a bit on that, AI can be used to provide automated insights from, for example, reading earnings transcripts, scanning social media and financial media. It can identify relationships between securities and market indicators that traditional analysis would not expect or identify relationships between securities and nonmarket data, such as weather patterns, that have predictive value. It can also offer synthetic data generation to improve financial models and ensure compliance with privacy regulations. With algorithmic trading estimated to account for somewhere between 60% to 73% of equity trading in the United States, the potential for AI to impact the markets is profound.
What if we get more specific with ChatGPT?
Q: What was the return for the S&P 500 in 2022?
A: As an AI language model, I do not have access to future events or data. I apologize for not being able to provide the return for the S&P 500 in 2022.
So that was a bust on multiple fronts. What about something more generic concerning how to structure a portfolio?
Q: What has historically been the best investment portfolio allocation?
A: There is no one “best” investment portfolio allocation that fits everyone as it varies depending on an individual’s risk tolerance, investment goals, time horizon, and financial situation. However, a commonly used rule of thumb is the 60/40 portfolio allocation, where 60% of the portfolio is invested in stocks and 40% in bonds. This allocation is based on historical data that suggests stocks have higher returns but come with higher volatility, while bonds offer lower returns but serve as a safer and more stable investment option. It is essential for investors to regularly review and adjust their investment portfolios based on changes in their financial situation and market conditions.
That’s the standard generic answer you’d get most anywhere, so no real value added. What about if we ask for some forecasting?
Q: What will be the best-performing sector in 2023?
A: As an AI language model, I cannot predict the future with certainty. However, based on the current trend and projections, the technology sector is expected to continue to perform well in the coming years. With the increasing demand for digital products and services and the growth of emerging technologies such as artificial intelligence, machine learning, and the Internet of Things (IoT), the technology sector is expected to remain a strong performer in the years to come.
Not much of a shocker here, but dare I suggest that there may be a bit of personal bias? What if we try to get more specific?
Q: What will be the strongest performing stock of 2023?
A: As an AI language model, I do not have the capability to predict future events or market trends. Stock performances are subject to various factors and uncertainties that make it difficult to predict which stock will perform the strongest in any given year. It is recommended that you seek advice from a financial advisor and conduct your own thorough research before making any investment decisions.
Well done by OpenAI’s compliance department.
Companies to Watch
For investors looking to harness the power of AI for their investment portfolios and want something more than ChatGPT’s handwave, here are some companies offering just that.
- AlphaSense is an AI-based market intelligence and search platform that gathers insights from an extensive library of public and private sources including earnings call transcripts, SEC filings, and industry journal articles. The company just closed its latest round of funding at a $1.8 billion valuation, with investors such as Alphabet’s (GOOG) CapitalG, Goldman Sachs and Viking Global Investors.
- Trading Technologies International is an AI platform that identifies complex trading patterns on a massive scale across multiple markets in real time. By combining machine learning technology with high-speed, big data processing power, the company gives clients the ability to build their own algorithm trading platforms, automating the entry and exit of positions and reducing the market impact of large orders as well as the risk of manual errors. The company has pricing plans for individuals, pro investors, and organizations.
- Kavout Corporation provides an AI-driven investment platform built for investors of all levels.
- IntoTheBlock uses AI to generate price forecasts and quantitative trading strategies for crypto markets.
Original Article: https://www.nasdaq.com/articles/what-to-know-about-the-growing-impact-of-ai-in-financial-services
