Five generative AI use cases for the financial services industry Google Cloud Blog

This process facilitates the model’s capacity to tailor its output in alignment with the newly incorporated training data. GenAI would likely bring about systemic risks similar to those of AI/ML, but it would also bring its own concerns. These concerns could be exacerbated by the ease and cost-effectiveness with which GenAI reports can be generated and the lack of effective regulatory regime. This environment could increase the temptation for excessive reliance on GenAI, which, in turn, could increase contagion risk and build systemic risks in the financial sector. As highlighted in the IMF 2021 paper, AI/ML could potentially bring about new sources and transmission channels of systemic risks.

• 2023 was a game-changing year for business, with an explosion of interest in generative artificial intelligence.
• The analyst formats the content into a Word document and readies it for an initial review by his manager.
• He has also led commercial growth of deep tech company Hypatos that reached a 7 digit annual recurring revenue and a 9 digit valuation from 0 within 2 years.
• Bias could emerge if the data used to train the system are incomplete or unrepresentative, or the data are underpinned by prevailing societal prejudices.
• The users represented a broad spectrum (for example, industries, academia, legal firms, and publishing houses), all of which have started leveraging the technology’s capabilities.
• For Generative AI, this translates to tools that create original content modalities (e.g., text, images, audio, code, voice, video) that would have previously taken human skill and expertise to create.

After just four months, generative AI was doing the work equivalent to 50 full-time employees on an annualized basis. Employees experienced a 10% net reduction of the work coming into the customer support call center. To ensure that all parts of the business can scale gen AI capabilities, centralizing competencies is a natural first move. The critical focus for this central team will be to develop and put in place protocols and standards to support scale, ensuring that teams can access models while also minimizing risk and containing costs. The team’s work could include, for example, procuring models and prescribing ways to access them, developing standards for data readiness, setting up approved prompt libraries, and allocating resources. While current upskilling is largely based on a “learn on the job” approach, we see a rapid market emerging for people who have learned these skills over the past year.

A high-performing finance function understands the use cases that could most significantly and feasibly improve their function (Exhibit 2). Regulatory policy will evolve over time to help guide the use of GenAI applications by financial institutions, but interim actions are needed. You can foun additiona information about ai customer service and artificial intelligence and NLP. Prudential oversight authorities should strengthen their institutional capacity and intensify their monitoring and surveillance of the evolution of the technology, paying close attention to how it is applied in the financial sector.

Generative AI (gen AI) is a predictive language model that produces new unstructured content such as text, images, and audio. Traditional, or analytical, AI, by contrast, is used to solve analytical tasks such as classifying, predicting, clustering, analyzing, and presenting structured data. Current GenAI models are increasingly subject to successful “jailbreaking” attacks (see, for example, ADVERSA 2023).

There’s a broad industry consensus that systems powered by large language models like ChatGPT and Gemini will profoundly affect how we interact with our devices. ServiceNow is betting big on generative artificial intelligence to drastically change the software it sells and the people who sell it. As part of the tool, it listed all the guardrails that had been put in place, and for each answer provided a link to the sentence or page of the relevant policy documents. The company also used an LLM to generate many variations of the same question to ensure answer consistency. These steps, among others, were critical to helping end users build trust in the tool. Their LQAI ETF, which launched in November and relies on a proprietary AI stockpicking tool, has evolved to incorporate an AI-generated monthly holdings report.

Figure out where gen AI copilots can give you a real competitive advantage

But bold CFOs put their finance team in the best position to learn to work with these tools as the technology gains momentum. A world-class CFO ensures that these and other gen AI initiatives aren’t starved of capital. Indeed, one of the biggest misconceptions we find is the belief that it’s the job of the CFO to wait and see—or, worse, be the organization’s naysayer. The best CFOs are at the vanguard of innovation, constantly learning more about new technologies and ensuring that businesses are prepared as applications rapidly evolve. LLMs are machine learning models that are good at understanding questions or requests and generating human language. Those models operate by ingesting vast quantities of data, for training purposes, to discern statistical patterns, including the relationships between words and the contextual significance of each word within a sentence.

Gen AI isn’t just a new technology buzzword — it’s a new way for businesses to create value. While gen AI is still in its early stages of deployment, it has the potential to revolutionize the way financial services institutions operate. Gen AI, along with its boost to productivity, also presents new risks (see sidebar “A unique set of risks”). Risk management for gen AI remains in the early stages for financial institutions—we have seen little consistency in how most are approaching the issue.

Some or all of the services described herein may not be permissible for KPMG audit clients and their affiliates or related entities. The information contained herein is of a general nature and is not intended to address the circumstances of any particular individual or entity. Although we endeavor to provide accurate and timely information, there can be no guarantee that such information is accurate as of the date it is received or that it will continue to be accurate in the future. No one should act upon such information without appropriate professional advice after a thorough examination of the particular situation. Sometimes, customers need help finding answers to a specific problem that’s unique and isn’t pre-programmed in existing AI chatbots or available in the knowledge libraries that customer support agents can use. That kind of information won’t be easily available in the usual AI chatbots or knowledge libraries.

Evaluate whether the optimal approach is creating a center of excellence or embedding AI capabilities into technology teams. Generative AI has the potential to transform Finance, and business, as we know it. According to a Gartner study, 80% of CFOs surveyed in 2022 expected to spend more on AI in the coming two years.2 With that investment, however, around two-thirds think their function will reach an autonomous state within six years.

Business leaders are excited about generative AI (gen AI) and its potential to increase the efficiency and effectiveness of corporate functions such as finance. A May 2023 survey of around 75 CFOs at large organizations found that almost a quarter (22 percent) were actively investigating uses for gen AI within finance, while another 4 percent were pursuing pilots of the technology. In today’s rapidly evolving landscape, the successful deployment of gen AI solutions demands a shift in perspective—that is, starting with the end user experience and working backward. This approach entails a rethinking of processes and the creation of AI agents that are not only user-centric but also capable of adapting through reinforcement learning from human feedback. This ensures that gen AI–enabled capabilities evolve in a way that is aligned with human input. CFOs cannot afford to stand on the sidelines as generative AI reshapes the finance function of the future and its partner functions, such as marketing and HR.

Ensure data quality and focus on unstructured data to fuel your models

Cem’s work has been cited by leading global publications including Business Insider, Forbes, Washington Post, global firms like Deloitte, HPE, NGOs like World Economic Forum and supranational organizations like European Commission. Financial institutions can benefit from sentiment analysis to measure their brand reputation and customer satisfaction through social media posts, news articles, contact centre interactions or other sources. Banks want to save themselves from relying on archaic software and have ongoing efforts to modernize their software. Enterprise GenAI models can convert code from old software languages to modern ones and developers can validate the new software saving significant time.

Furthermore, embracing cross-domain and cross-functional applications of AI holds immense potential. Imagine AI systems seamlessly conversing across different facets of finance, from payments to collections, unlocking synergies and driving efficiencies at every turn. While we’re not quite there yet, laying the groundwork now sets the stage for future innovation and collaboration. Balancing considerations of security, efficiency and team readiness is essential for success. By acknowledging these requirements and strategizing accordingly, organizations can navigate the complexities of adoption and unlock the transformative potential of generative AI in financial management.

We bring together passionate problem-solvers, innovative technologies, and full-service capabilities to create opportunity with every insight. KPMG has market-leading alliances with many of the world’s leading software and services vendors. Financial services leaders are no longer just experimenting with gen AI, they are already way building and rolling out their most innovative ideas. Gen AI can give developers context about the underlying regulatory or business change that will require them to change code by providing summarized answers with links to a specific location that contains the answer. It can assist in automating coding changes, with humans in the loop, helping to cross-check code against a code repository, and providing documentation.

At the heart of GenAI are large language models (LLMs), which are neural network–based models trained on massive amounts of data, including text and documents, and capable of producing understandable and meaningful text or human languages (Appendix 2). LLMs enable a wide range of applications across various domains with significant implications for the global economy and financial sector. In recent years, technological advances and competitive pressures have fueled rapid adoption of artificial intelligence (AI) in the financial sector, and this adoption is set to accelerate with the recent emergence of generative AI (GenAI). GenAI is a significant leap forward in AI technology that enhances its utility for financial institutions that have been quick at adapting it to a broad range of applications. GenAI could aggravate some of these risks and bring about new types or risks as well, including for financial sector stability. This paper provides early insights into GenAI’s inherent risks and their potential impact on the financial sector.

Solutions such as OpenAI’s ChatGPT are available online, and other applications (including McKinsey’s Lilli) are already in use. Financial institutions’ reliance on GenAI technologies from a small number of providers could result in concentration risk and lead to making those providers vulnerable to various operational risks or disruptions. The high dependence of financial business and the technological concentration could create a “too-big-to-fail” problem. Given that GenAI technology is a relatively new phenomenon, the full scale of its vulnerability to cyberattacks is yet to be comprehensively understood.

Gen AI models can also produce wildly incorrect financial reports; the product appears flawless, but the line items don’t apply to the company and the math looks like it should sum but doesn’t. What seems like a real 10-K form on the first flip through may be wholly untethered from reality. GenAI models face different challenges to performance robustness, reflecting the nature of GenAI’s data environment and decision-making process. An important challenge for AI systems is embedded bias—particularly in a highly regulated and sensitive sector like financial services. Embedded bias could be defined as computer systems that systematically and unfairly discriminate against certain individuals or groups of individuals in favor of others (Friedman and Nissenbaum 1996).

For all its tantalizing potential to automate and augment processes, generative AI will still require human talent. The hotel guest management technology company’s platform digitizes the hotel guest journey from post-booking through checkout. A TechCrunch review of LinkedIn data found that Ford has built this team up to around 300 employees over the last year. Apple is expected to announce a partnership with OpenAI that will bring the company’s smarts to the iPhone and Mac. Apple’s near-term strategy is a deep integration between existing properties and generative AI, with Siri at the center.

Deloitte shall not be responsible for any loss sustained by any person who relies on this publication. Despite this, 60% of surveyed BFM CEOs say they are pushing for AI adoption more quickly than some employees might find comfortable. Yet 43% acknowledged that their employees do not fully understand how strategic decisions impact them. The findings also revealed that CEOs are navigating complex issues around culture in the era of AI.

Another unfocused effort we often see is when companies move to incorporate gen AI into their customer service capabilities. Customer service is a commodity capability, not part of the core business, for most companies. While gen AI might help with productivity in such cases, it won’t create a competitive advantage. Let’s briefly look at what this has meant for one Pacific region telecommunications company.

On commercial cloud services, employing the Nvidia A100 GPU (used for Llama 2) can set one back by $1-$2 for every GPU hour. Doing the math, a 10 billion parameter model could cost around $150,000, while a 100 billion parameter model could cost as high as $1,500,000. In addition, 66% of BFM CEOs surveyed stated that the potential productivity gains from automation are so great that they would accept significant risks to stay competitive, with 67% saying they would risk more than their competitor to maintain competitive edge. With tools such as ChatGPT, DALLE-2, and CodeStarter, generative AI has captured the public imagination in 2023. Unlike past technologies that have come and gone—think metaverse—this latest one looks set to stay. It reached 100 million monthly active users in just two months after launch, surpassing even TikTok and Instagram in adoption speed, becoming the fastest-growing consumer application in history.

I half expected an announcement along those lines at I/O last month, though I’m glad it ultimately opted to give Gemini more time to bake. When something is prioritized above trusted resources in the world’s dominate search engine, it needs to get things right as much as humanly possible, and not, you know, tell people to eat glue. Google labels Gemini results a product of its “Search Labs,” but surely a majority of users don’t understand what that means in terms of product maturity, nor can they be bothered to click through for more information. The presentation’s stakes are far higher than your standard post-event market moves. The pressure for Tim Cook and crew to deliver the goods is, in a very real sense, even higher than it was in the lead up to last year’s Vision Pro announcement.

Watch this video to learn how you can extract and summarize valuable information from complex documents, such as 10-K forms, research papers, third-party news services, and financial reports — with the click of a button. If you look at just a few of the Generative AI applications this model renders, it also becomes apparent why it has captivated the attention of both society and the business world across the spectrum of industries. Banks that foster integration between technical talent and business leaders are more likely to develop scalable gen AI solutions that create measurable value. To further demystify the new technology, two or three high-profile, high-impact value-generating lighthouses within priority domains can build consensus regarding the value of gen AI. They can also explain to employees in practical terms how gen AI will enhance their jobs. The Deloitte AI Institute helps organizations transform through cutting-edge AI insights and innovation by bringing together the brightest minds in AI services.

DTTL (also referred to as “Deloitte Global”) does not provide services to clients. In the United States, Deloitte refers to one or more of the US member firms of DTTL, their related entities that operate using the “Deloitte” name in the United States and their respective affiliates. Certain services may not be available to attest clients under the rules and regulations of public accounting. CFOs and Finance leaders can play a pivotal role in driving strategic collaboration among key C-suite leaders to enable greater success—and return on investment—of AI deployment and adoption. The journey should begin with a sound strategy and a few use cases to test and learn with well-governed and accessible data.

For the wide range of use cases of conversational AI for customer service operations, check our conversational AI for customer service article. In this article, we explain top generative AI finance use cases by providing real life examples. These examples illustrate how generative artificial intelligence is revolutionizing the field by automating routine tasks and analyzing historical finance data. If your focus is just banking, a subset of these use cases are listed in generative AI use cases in banking. We tapped into the minds of our very own F&A experts at IBM Consulting — the ones that know that how you help businesses make data-driven decisions indicates your ability to support future business.

The JPMorgan tool — part of the $3.2tn manager’s Spectrum portfolio management platform, which is fuelled by about 40 years of data — is a pilot program that is still in development and will be made available to a broader group of portfolio managers later this year. JPMorgan later this year plans to expand the use of a generative AI tool that https://chat.openai.com/ flags questionable decisions by portfolio managers, such as potentially selling top-performing stocks too soon, company officials told the Financial Times. With an expanded number of companies and a dynamic analysis, Lee can formulate more holistic observations and recommendations based on deeper data analysis than under the previous process.

Whether you’re a CFO, an accountant, a financial analyst or a business partner, artificial intelligence (AI) can help improve your finance strategy, uplift productivity and accelerate business outcomes. Though it may feel futuristic, advancements such as generative AI and conversational AI technology can benefit Finance & Accounting (F&A) now. Instead, it’s the CFO’s role to allocate resources at the enterprise level—rapidly, boldly, and disproportionately—to the projects that create the most value, regardless of whether they are driven by gen AI. Similarly, in leading the finance function, the CFO can’t implement gen AI for everyone, everywhere, all at once.

Participants included IT decision-makers, business decision-makers, and CXOs from 1,000+ employee organizations considering or using AI. Participants did not know Google was the research sponsor and the identity of participants was not revealed to Google. For example, gen AI can help bank analysts accelerate report generation by researching and summarizing thousands of economic data or other statistics from around the globe. It can also help corporate bankers prepare for customer meetings by creating comprehensive and intuitive pitch books and other presentation materials that drive engaging conversations. Picking a single use case that solves a specific business problem is a great place to start. It should be impactful for your business and grounded in your organization’s strategy.

While rumors point to the company transitioning a number of employees to generative AI operations following its electric car implosion, all signs point to Apple having ceded a significant head start to the competition. As such, its most logical play is a partnership with a reigning powerhouse like OpenAI. Billionaire Elon Musk blasted the Apple iPhone’s integration of ChatGPT as “creepy spyware” and vowed to ban the devices from his companies (Tesla, X, SpaceX, etc.) unless Apple reverses course. Whether the newly announced Apple-OpenAI integration actually presents the security risk Musk suggests is up for debate. Apple said that iPhone users have the final say on what data they share with OpenAI—if Siri thinks ChatGPT can help, it will ask permission to share the question and present the answer directly from the chatbot.

Generative AI refers to models that can generate new data samples that are similar to the input data. The success of ChatGPT opened many opportunities across industries, inspiring enterprises to design their own large language models. Generative AI models, when fine-tuned properly, can generate various scenarios by simulating market conditions, macroeconomic factors, and other variables, providing valuable insights into potential risks and opportunities. Specialized transformer models help finance units in automating functions such as auditing, accounts payable including invoice capture and processing. With deep learning functions, GPT models specialized in accounting can achieve high rates of automation in most accounting tasks.

However, AI/ML models face a more challenging task when previously reliable signals become unreliable or when behavioral correlations shift significantly, leading to a loss in prediction accuracy. The ability to track event-driven news exists today, and many hedge funds and quants have developed ways to trade the markets based on signals from news and social media sentiment, confidence, and story counts. Knowledge workers will evolve their focus from searching for, aggregating, and summarizing key sections of text and images to checking the accuracy and completeness of answers provided by generative AI models. About the Google Cloud Generative AI Benchmarking StudyThe Google Cloud Customer Intelligence team conducted the Google Cloud Generative AI Benchmarking Study in mid-2023.

For slower-moving organizations, such rapid change could stress their operating models. But customer relationships may be tested when determining whether a fraud loss is to be borne by customers or their financial institutions. Customers expect efficiency and security when using their money, and generative AI’s deepfake technology could disrupt these two goals. Banks have an opportunity to educate consumers and build awareness about potential risks and how the bank is managing them. Building this level of awareness will likely require frequent communication touchpoints, such as push notifications on banking apps that warn customers of possible threats.

As companies including Live Nation and Advanced Auto Parts investigate potential breaches, Snowflake has been encouraging clients to impose stronger security controls. The list of those impacted by the data theft may soon grow, as security firm Mandiant and Snowflake have notified at least 165 Snowflake customers that they may have been compromised. Mandiant also said there was no evidence that Snowflake’s enterprise environment was breached. To get the business up to speed, ServiceNow mandated that every department needed to develop an AI roadmap.

With LLMs, firms can automatically translate complex questions from internal users and external customers into their semantic meaning, analyze for context, and then generate highly accurate and conversational responses. Specifically, LLMs enable long-form answers to open-ended questions (e.g., search thousands generative ai in finance of pages of legal or technical documentation and summarize the key points that answer the question). It is the combination of a predominant mindset, actions (both big and small) that we all commit to every day, and the underlying processes, programs and systems supporting how work gets done.

Naturally, banks encounter distinct regulatory oversight, concerning issues such as model interpretability and unbiased decision making, that must be comprehensively tackled before scaling any application. Leaders must acquire a deep personal understanding of gen AI, if they haven’t already. Investments in executive education will equip them to show employees precisely how the technology and the bank’s operations connect, thereby generating excitement and overcoming trepidation. Tools like generative AI could work wonders for individuals, businesses, and society. And since Finance draws upon enormous amounts of data, it’s a natural fit to take advantage of generative AI.

Given the frequency with which their developers toss around the phrase “general purpose humanoids,” more attention ought to be paid to the first bit. After decades of single-purpose systems, the jump to more generalized systems will be a big one. While Gemini hasn’t completely conquered Android yet, however, Google is clearly signaling at a day in the not too distant future when it replaces Assistant outright.

For example, a global financial institution seeking to implement generative AI in its payment processing system would prioritize encrypting sensitive customer data and implementing multifactor authentication protocols to mitigate security risks. The CFO is often a company’s de facto chief risk officer, and even when a company already has a separate risk team (as is the case, for example, with financial institutions), CFOs remain a key partner in helping to identify and mitigate risks. Financial institutions are required to be able to explain their decisions and actions, internally and to external stakeholders, including prudential supervisors.

Schrage was the guest speaker last night at Fortune’s CFO Collaboration dinner, in partnership with Workday and Deloitte, at Mourad in San Francisco. He talked with our community of finance chiefs from across the Bay Area about tech trends and how digitalization impacts capital allocation. Financial services firms have started to adopt generative AI, but hurdles lie in their path toward generating income from the new technology. He has also led commercial growth of deep tech company Hypatos that reached a 7 digit annual recurring revenue and a 9 digit valuation from 0 within 2 years. Cem’s work in Hypatos was covered by leading technology publications like TechCrunch and Business Insider. This automation not only streamlines the reporting process and reduces manual effort, but it also ensures consistency, accuracy, and timely delivery of reports.

• In 2020 and 2022, the share of workers with the shortest tenure levels increased, while the share with the longest tenure levels also increased.
• That kind of information won’t be easily available in the usual AI chatbots or knowledge libraries.
• The critical focus for this central team will be to develop and put in place protocols and standards to support scale, ensuring that teams can access models while also minimizing risk and containing costs.
• Those realities make it even more important for CFOs to get started in a considered and proactive way.
• Institutions must reflect on why their current operational structure struggles to seamlessly integrate such innovative capabilities and why the task requires exceptional effort.

Helping clients meet their business challenges begins with an in-depth understanding of the industries in which they work. In fact, KPMG LLP was the first of the Big Four firms to organize itself along the same industry lines as clients. KPMG’s multi-disciplinary approach and deep, practical industry knowledge help clients meet challenges and respond to opportunities. MSCI is also partnering with Google Cloud to accelerate gen AI-powered solutions for the investment management industry with a focus on climate analytics. ARTIFICIAL INTELLIGENCE (AI) is the theory and development of computer systems able to perform tasks normally requiring human intelligence. CEOs who take the lead in implementing Responsible AI can better manage the technology’s many risks.

New research out of MIT points to how the latter might profoundly affect the former. CIOs, CFOs, and other C-suite leaders are still sorting out where to best deploy the fast-evolving tech without overspending, and how to prove a return on investment when they spend millions to infuse AI to their business. “Tech transformations can be costly, complex initiatives, and the data shows that companies continue to struggle with unlocking real value from them,” says Chat GPT PwC. More than half of executives “agree” or “strongly agree” that they are behind the competition in adopting new technologies, a new survey of 673 U.S. executives from PwC shows, up from 48% in August 2023. Costs are the top internal challenge that may be preventing companies’ efforts to reinvent their business, followed by changes to the operating model to support a company’s new vision and achieving measurable value from adopting new technologies.

The TechSprint culminates in a Demo Day where each team will present its ideas to an independent panel of judges drawn from subject matter experts in government, industry, nonprofits, and academia. First thing in the morning, Lee checks her phone’s GenAI-aggregated news feed to catch up on overnight markets and industry news. Recent estimates by McKinsey suggest that this Generative AI could offer annual savings of up to $340 billion for the banking sector alone. BFM CEOs are hedging their bets on generative AI to stay competitive and are willing to take risks to achieve this.

The integration of knowledge graphs with LLMs holds the potential to yield more precise, dependable, and contextually aware responses, marrying the humanlike language generation capabilities of LLMs with the factual consistency and the accuracy of knowledge graphs. Nevertheless, the seamless integration of these two systems presents a complex challenge and remains an active area of investigation within the field of AI. There are ongoing efforts at present to address GenAI hallucination, but they are narrowly focused on specific tasks (for example, abstractive summarization) rather than on addressing the problem from a broader perspective (Ji and others 2023). Efforts to develop enterprise-level GenAI could help minimize the problem by providing more focused, better quality, and more transparent training data.

It is a language model built from scratch with 50 billion parameters, tailored specifically for financial data. Every financial service aims to craft its own fine-tuned LLMs using open-source models like LLAMA 2 or Falcon. The number of M&A deals in the global banking sector dropped 19.6% year over year to 505 in 2022—the lowest number of deals in five years, according to a new analysis by S&P Global Market Intelligence. North America, which accounts for the highest number of bank M&A, had a 24.6% decline in the number of deals in 2022 to 304, according to the report.