Where are the investment opportunities in AI?

Authors: Stephanie Roth, Bruno de la Sota, Weiheng Chen, Cynthia Chou

Market Update

It was an eventful couple of weeks for markets. The House and Senate have passed a debt ceiling deal that was negotiated between President Biden and House Speaker McCarthy over many weeks and it is expected to be signed into law ahead of the June 5^th “X-date”, thus averting a debt ceiling breach. The agreement will suspend the debt ceiling until January 2025, with some spending caps for the next two years, but is generally not expected to significantly impact the macro outlook. In the wake of resilient macro data markets have moved to price in another 25bps hike from the Fed between June and July this year, with Fed officials divided on a pause or further hikes. The May payrolls report on June 2^nd will likely be a key data point for determining the near-term path for monetary policy. Amidst the news flow, risk assets have broadly held steady, with notable gains in the tech sector.

A remarkable market move was NVIDIA, which saw a 25% surge in its stock price last week. Earnings exceeded expectations by 19% and revenues by 10%. Their forward guidance anticipated Q2 sales of $11bn (an impressive ~$4bn ahead of consensus). Most of this outperformance and optimism was driven by the recent AI boom, which is further fueling semiconductor demand.

AI is a groundbreaking technology that could accelerate the next era of innovation and efficiency. Since its launch in November 2022, ChatGPT has taken the world and the media by storm – with this rapid ascent raising some fundamental questions about the nature of AI, and what it means for the broader economy. This week’s note assesses the potential economic impact of AI, and considers some investment opportunities.

Strategy Question: Where are the investment opportunities in AI?

OpenAI launched GPT-3.5 in November of 2022. The public prototype quickly gained traction, reaching 1 million users in just five days. By January 2023, it surpassed the 100 million user mark, making it one of the fastest growing platforms ever.

The ChatGPT application uses the large language model (LLM), which distinguishes itself from the traditional chatbot by making itself look and feel like a genuine human interaction – with a great level of expertise across a wide range of topics. LLMs have the potential to redefine how we approach daily tasks by increasing efficiency and improving utility and engagement. A number of large tech companies soon followed the interest, announcing multi-year commitments to this type of generative AI.

Generative AI investments will likely focus on three layers: 1) Applications that integrate AI models into user-facing products, 2) Models that power AI products running on proprietary models (or on open source) and 3) Infrastructure vendors that run the computing power required to service the models. As key players start to position, we would expect investments in the following segments for commercial AI applications:

1. Productivity and Efficiency Applications
This can be illustrated by an example: GitHub Copilot (acquired by Microsoft in October 2018) shares autocomplete-style suggestions from an AI pair programmer as you code. In March 2023, Microsoft introduced Copilot to a small number of enterprises and individuals, testing the integration of ChatGPT into Office365. Copilot in Word gives users a first draft to edit and iterate, eliminating the worry of writer’s block. Copilot in PowerPoint helps create presentations with a simple prompt. The Excel iteration analyzes trends, creating professional-looking data visualizations in seconds. With Teams, those late to meetings will be able to get a summary transcript of what they missed. Copilot could even assist with the organization of Outlook inboxes.

It’s only a matter of time until companies decide to monetize improvements in utility. However, the real advancement will only be as good as the underlying data in which the algorithm is trained on.

2. Cloud Infrastructure
Running queries on large datasets can increase workloads on the public cloud infrastructure. The scaling needed to satisfy the demand for computing power will only put upward pressure on infrastructure investment. It is here that having a cloud partner – like Microsoft Azure, Amazon Web Services or Google Cloud Platform – is key to developing a solid LLM.

3. Computing Power and Chips
Estimates on the capacity required to absorb increasing workloads range widely. Some forecasts expect unit shipments for AI datacenters to double from ~7% today to ~15% by 2027, and revenue to grow from ~20% today to ~45% by 2027. That expansion appears to be driven by a 3x-10x increase in AI server costs.

What does AI mean for the economy and labor market?

Let’s get in the spirit by asking ChatGPT: “Artificial intelligence can have a positive impact on economic growth in a number of ways: 1) Increased productivity: AI can automate routine tasks and perform them faster and more accurately than humans, which can increase productivity and output; 2) Cost savings: By automating tasks and processes, AI can reduce labor costs; 3) New business opportunities: AI can help businesses identify new opportunities for growth and innovation; 4) Improved decision-making: AI can help businesses make more informed and data-driven decisions. However, it is important to note that some industries may see greater benefits than others, and the impact of AI on employment and income inequality also needs to be considered.”

Our take: Just like disruptive innovations of the past, AI is likely to boost the productivity of the U.S. economy. Jobs may be displaced during the rebalancing process, but growing pains could give way to new jobs and greater worker output.

Estimates are wide-ranging, but many suggest company productivity improves by 2-4% when AI is adopted. Around 25% of companies are expected to embrace AI in a meaningful way and that could amount to an annual productivity boost to GDP of 0.5%.

How will AI impact the labor market?

ChatGPT: “Artificial intelligence has the potential to automate many jobs that are currently performed by humans, which can lead to job displacement in certain industries. However, it's important to note that AI can also create new job opportunities and change the nature of work. Some jobs may see more automation than others, and some industries may see a greater demand for workers with AI-related skills. Jobs that require creativity, social intelligence, or physical dexterity, are less likely to be automated by AI.”

Our take: AI will likely impact the labor market, much like the advent of prior technological innovations. To maximize profits, U.S. corporations have often found cheaper labor abroad and/or automated processes. As we look forward, “the race between automation and augmentation” is on. Goldman Sachs estimates that 25% of current work tasks could be automated by AI in the U.S. and Europe. They find that traditionally high-skill, nonroutine jobs are highly susceptible to automation from AI (such as legal & financial operations). Meanwhile, manually intensive jobs or roles that require interpersonal skills are less susceptible (such as construction or personal care).

What comes next?

Expect more companies to announce multi-year commitments with OpenAI, or share developments on their own language processing models. The opportunities are immense, and it remains unclear who will lead the race of innovation. What is clear is that the battle is not just between the technology companies, and it’s not just winner takes all. In an era of efficiency and productivity, those that respond the quickest will lead. The incumbents have a head start, but new players will undoubtedly emerge.

Where are the investment opportunities?

Many (if not most) of the fast-growing disruptors that could drive innovation in the coming years are early-stage private companies. To access such opportunities means turning to private market investing, and AI could be a key source of growth for private and venture investors.

In public equities, semiconductor companies with strong AI and data center footprints are the most direct beneficiaries from the rising adoption of generative AI. In order to train LLMs, the demand for computing power is expected to grow 3-5x in the next five years, and disproportionately benefits GPU manufacturers. Although less geared, requirements for inference are still expected to benefit other manufacturers, who will likely compete for a robust and growing addressable market that could expand by 10x over the next five years. In Asia, high-end foundries that manufacture AI-related integrated circuits are set to see rapidly-growing demand, supported by a substantial improvement of their CoWoS (Chip-on-Wafer-on-Substrate) capacity in 2H23. Memory makers could also benefit from rising demand. With the growing demand for high performance computing chips (HPC), capacity growth could benefit semi equipment makers with a portfolio geared towards HPC. Much of these exponentially growing calculations will likely be taking place in data centers and benefit the large hyperscalers that provide this capacity as a service. Finally, numerous software firms are increasingly embracing and incorporating AI in their work practices and products, which could in turn bring new revenue opportunities. Given that software has lagged the move higher in semiconductors, this group could offer attractive catch-up opportunities.

All market and economic data as of June 1, 2023 and sourced from Bloomberg Finance L.P. and FactSet unless otherwise stated.

For illustrative purposes only. Estimates, forecasts and comparisons are as of the dates stated in the material.

There can be no assurance that any or all of these professionals will remain with the firm or that past performance or success of any such professional serves as an indicator of the portfolio’s success.

We believe the information contained in this material to be reliable but do not warrant its accuracy or completeness. Opinions, estimates, and investment strategies and views expressed in this document constitute our judgment based on current market conditions and are subject to change without notice.

This document may also have been made available in a different language, at the recipient’s request, and for convenience only. Notwithstanding the provision of a convenience copy, the recipient re-confirms that he/she/they are fully conversant and has full comprehension of the English language. In the event of any inconsistency between such English language original and the translation, including without limitation in relation to the construction, meaning or interpretation thereof, the English language original shall prevail.

This information is provided for informational purposes only. We believe the information contained in this video to be reliable; however we do not represent or warrant its accuracy, reliability or completeness, or accept any liability for any loss or damage arising out of the use of any information in this video. The views expressed herein are those of the speakers and may differ from those of other J.P. Morgan employees, and are subject to change without notice. Nothing in this video is intended to constitute a representation that any product or strategy is suitable for you. Nothing in this document shall be regarded as an offer, solicitation, recommendation or advice (whether financial, accounting, legal, tax or other) given by J.P. Morgan and/or its officers or employees to you. You should consult your independent professional advisors concerning accounting, legal or tax matters. Contact your J.P. Morgan team for additional information and guidance concerning your personal investment goals.

Indices are not investment products and may not be considered for investment.

For illustrative purposes only. This does not reflect the performance of any specific investment scenario and does not take into account various other factors which may impact actual performance.

These are presented for illustrative purposes only. Your actual portfolio will be constructed based upon investments for which you are eligible and based upon your personal investment requirements and circumstances. Consult your J.P. Morgan representative regarding the minimum asset size necessary to fully implement these allocations. 

Past performance is not a guarantee of future results. It is not possible to invest directly in an index.

Investing in alternative assets involves higher risks than traditional investments and is suitable only for sophisticated investors. Alternative investments involve greater risks than traditional investments and should not be deemed a complete investment program. They are generally not tax efficient and an investor should consult with his/her tax advisor prior to investing. Alternative investments have higher fees than traditional investments and they may also be highly leveraged and engage in speculative investment techniques, which can magnify the potential for investment loss or gain. The value of the investment may fall as well as rise and investors may get back less than they invested.

RISK CONSIDERATIONS 

• Past performance is not indicative of future results. You may not invest directly in an index. 
• The prices and rates of return are indicative as they may vary over time based on market conditions. 
• Additional risk considerations exist for all strategies. 
• The information provided herein is not intended as a recommendation of or an offer or solicitation to purchase or sell any investment product or service. 
• Opinions expressed herein may differ from the opinions expressed by other areas of J.P. Morgan. This material should not be regarded as investment research or a J.P. Morgan investment research report.