The topic of how artificial intelligence can transform banking continues to get a massive amount of attention. With data in abundance, and the need to improve efficiency and create better customer experiences, every new evolution of AI creates opportunities, while also raising questions around privacy, biases, the impact on the human workforce, and changes in existing business models.
One of the most talked about advances in the deployment of AI occurred on November 30, when OpenAI released ChatGPT, deemed “the most advanced, user-friendly chatbot to enter the public domain.” ChatGPT can create high-level content, respond to customer inquiries, assist with research, and provide perspectives on current trends.
OpenAI, a nonprofit company, was founded in 2015 by Sam Altman, Elon Musk and other Silicon Valley investors. Musk stepped down from the board in 2018, but remains an investor. According to Altman, who is OpenAI’s chief executive, ChatGPT reached 1 million users in less than one week. While ChatGPT is free to use at this time, the future monetization of this impressive artifical intelligence platform is certainly possible.
“ChatGPT is one of those rare moments in technology where you see a glimmer of how everything is going to be different going forward.”
— Aaron Levie, CEO of Box
Rather than creating an article about the technology, I thought it would be more interesting to interview ChatGPT about itself. I found the process not unlike doing a Banking Transformed podcast interview. The AI chatbot gave detailed, human-like answers to each question, generated in a matter of seconds. If I wasn’t satisfied with a response, I could ask ChatGPT to answer my question again — which is not much different than asking a follow-up question in any other interview — and I would receive a significantly different response. Read on to find out how ChatGPT says it can help marketers and improve innovation initiatives, and what it sees as the biggest trends and opportunities in the banking industry.
My introduction to set the tone for the interview with ChatGPT: “You are the latest of the large language chat models. I am a content creator wanting to learn more about you and your capability to help the banking industry. I’d like to interview you for an article in The Financial Brand and potentially for my podcast, Banking Transformed. You should respond in a conversational manner.” (Note: The following responses are from ChatGPT and have not been edited.)
Introduce yourself and share a little bit about your background.
ChatGPT chatbot: I’m an AI assistant, a large language model trained by OpenAI. I’m not a physical being, but rather a computer program designed to assist with a variety of tasks. I’ve been trained to understand and generate human-like text, which makes me a useful tool for many different applications, including the banking industry.
As a language model, my primary function is to understand and generate text, so I’m not directly involved in the banking industry. However, my ability to understand and provide information on a wide range of topics makes me a valuable resource for anyone working in the industry. I can help with tasks like answering customer questions, providing information on products and services, and even assisting with research and analysis.
Overall, my goal is to make it easier for people to access the information they need, and to help businesses like banks operate more efficiently and effectively. I’m constantly learning and improving, so my capabilities are always evolving. If you have any specific questions about how I might be able to help the banking industry, I’d be happy to try to answer them.
How were you trained?
ChatGPT chatbot: I was trained using a process called unsupervised learning, which involves feeding a large amount of text data into a computer program and allowing the program to learn from the data on its own. This type of training allows me to understand and generate human-like text, and to improve my capabilities over time as I continue to learn from new data.
In addition to this unsupervised training, I also receive regular updates and improvements from the team at OpenAI. These updates help me to refine my understanding of language and to improve my ability to assist with a wide range of tasks. Overall, my training is designed to help me provide accurate and helpful information to the best of my abilities.
“I can provide ideas and suggestions for marketing campaigns, create product descriptions, and even write blog posts and articles.”
— ChatGPT, in the interview with The Financial Brand
Are you a demonstration of AI capabilities or an open access product?
ChatGPT chatbot: As a large language model trained by OpenAI, I am currently a demonstration of the capabilities of modern natural language processing technology. I am not an open access product, and I do not have the ability to interact with the real world or perform any tasks outside of generating text at this time. I exist solely as a computer program designed to assist users with generating human-like text based on the input provided to me.
What is the advantage of ChatGPT compared to traditional chatbots?
ChatGPT chatbot: ChatGPT is a large, advanced language processing model that is trained using a technique called generative pre-trained transformer, or GPT. This allows ChatGPT to generate human-like responses to questions and statements in a conversation, making it a powerful tool for a wide range of applications.
Compared to traditional chatbots, which are often limited in their ability to understand and generate natural language, ChatGPT has the advantage of being able to provide more accurate and detailed responses. Additionally, because it is trained using a large amount of data, ChatGPT is able to learn and adapt to different conversational styles and contexts, making it more versatile and capable of handling a wider range of scenarios.
What weaknesses does ChatGPT have right now?
ChatGPT chatbot: As with any technology, ChatGPT has certain limitations and weaknesses that will be improved upon in future iterations of the technology. One potential weakness of ChatGPT is that it is a large, complex system that requires significant computational resources to run, which can make it difficult or expensive to use in some cases.
Additionally, because it is a machine learning system, my solution is only as good as the data it is trained on, which means that it can sometimes generate responses that are inaccurate or misleading if the training data is of poor quality. Finally, ChatGPT is not yet capable of understanding the full range of human language and meaning, which means that it may not always be able to provide a complete or accurate response to certain questions or statements.
However, as the technology continues to advance and improve, it is likely that these weaknesses will be addressed and overcome in future iterations of ChatGPT.
“ChatGPT is incredibly limited, but good enough at some things to create a misleading impression of greatness. It’s a mistake to be relying on it for anything important, but a preview of progress. We have lots of work to do on robustness and truthfulness.”
— Sam Altman, CEO of OpenAI
How can the banking industry best use ChatGPT technology?
ChatGPT chatbot: The banking industry can use ChatGPT technology in a number of ways to improve their operations and provide better service to their customers. For example, ChatGPT can be used to automate customer service tasks, such as answering frequently asked questions or providing detailed information about products and services. This can free up customer service representatives to focus on more complex or high-value tasks, improving overall efficiency and customer satisfaction.
Additionally, ChatGPT can be used to generate insights and analysis from large amounts of data, allowing banks to quickly and easily gain valuable insights into their operations and make better-informed decisions. In the future, ChatGPT technology is likely to become even more powerful and versatile, allowing banks to use it for a wider range of tasks and applications.
How can ChatGPT improve the customer experience?
ChatGPT chatbot: ChatGPT can help improve the customer experience in a number of ways. For example, they can be used to provide personalized and accurate answers to customer questions in real time, allowing for faster and more efficient resolution of customer inquiries. They can also be used to generate customized product or service recommendations based on a customer’s individual needs and preferences.
I can also assist with marketing content creation by generating human-like text that can be used in marketing materials. I can provide ideas and suggestions for marketing campaigns, create product descriptions, and even write blog posts and articles. However, it is important to note that I am a computer program and the text I generate may not always be suitable for use in marketing materials. It is recommended that the text I generate be reviewed and edited by a human before being used in any official capacity.
Finally, I can be used to help automate routine tasks, freeing up customer service representatives to focus on more complex and high-value activities. Overall, the use of large language models can help improve the customer experience by providing faster, more accurate, and more personalized support.
What routine tasks in banking can ChatGPT assist with?
ChatGPT chatbot: ChatGPT can be used to automatically process and classify incoming customer inquiries, such as by routing them to the appropriate department or customer service representative. It can also be used to help automate the completion of routine forms and paperwork, such as loan applications or account opening documents.
Additionally, large language models like ChatGPT can be used to assist with the analysis of customer data and transactions, such as by identifying potential fraud or unusual activity. Overall, the use of large language models can help improve the efficiency and accuracy of routine tasks in banking, freeing up human staff to focus on more complex and value-added activities.
How can ChatGPT help financial marketers?
ChatGPT chatbot: Bank marketers can leverage ChatGPT in several ways, including:
- Generating personalized and engaging content for marketing campaigns: ChatGPT can generate customized content based on customer data and preferences, making marketing messages more relevant and effective.
- Enhancing customer engagement and support: ChatGPT can be used to provide instant and personalized responses to customer inquiries, enhancing the customer experience and improving customer satisfaction.
- Conducting market research and analysis: ChatGPT can analyze customer data and feedback to provide insights and recommendations for market research and strategy development.
- Automating routine marketing tasks: ChatGPT can automate repetitive and low-value tasks, such as data entry and email marketing, freeing up human marketers to focus on more complex and value-added tasks.
Finally, I can also evaluate the effectiveness of marketing messages, campaigns and offers, identifying which ones are most likely to be successful with specific groups of customers.
Can ChatGPT improve innovation?
ChatGPT chatbot: Yes. ChatGPT can be used to generate new ideas and concepts by analyzing large amounts of data and identifying trends and patterns. They can also be used to evaluate the potential feasibility and viability of new ideas, and to help refine and develop those ideas into more concrete plans and proposals.
I can also be used to assist with the creative process by providing inspiration and suggestions for new directions and approaches. Overall, the use of large language models can help stimulate and support the innovation process by providing a source of new ideas and insights.
“Soon, you will be able to have helpful assistants that talk to you, answer questions and give advice. Eventually, you can have something that goes off and discovers new knowledge for you.”
— Sam Altman, CEO of OpenAI
Should banks democratize data and insights?
ChatGPT chatbot: Financial institutions should democratize data and insights in order to make it more widely available and easily accessible within the organization. This can be achieved by implementing data governance policies and practices that ensure that data is accurate, consistent, and accessible to all employees who need it. Additionally, financial institutions should invest in data analytics and reporting tools that make it easy for employees to access, analyze, and visualize data, regardless of their technical expertise.
Democratizing data and insights is important for several reasons. First, it allows employees at all levels of the organization to access the information they need to make informed decisions and drive business results. This can help to improve the quality and speed of decision-making, and can also foster a more data-driven culture within the organization.
Second, democratizing data and insights can help to improve the customer experience by enabling employees to access and analyze customer data in real-time, which can help to provide more personalized and relevant products and services. Finally, democratizing data and insights can also help to improve the efficiency and effectiveness of the organization by enabling employees to access and analyze data from multiple sources, which can help to identify trends and patterns that can be leveraged to drive growth and success.
What is your perspective on the future of banking?
ChatGPT chatbot: The future of retail banking is likely to involve a combination of traditional brick-and-mortar branches and increasingly sophisticated online and mobile banking services. Banks will continue to offer a range of financial products and services, including checking and savings accounts, loans, and investment options. However, the focus will shift towards providing personalized and convenient experiences for customers through the use of advanced technologies such as artificial intelligence, machine learning, and data analytics.
Banks will need to adapt to changing consumer preferences and the rise of alternative financial services providers, such as fintech startups and digital-only banks. This may involve partnering with or acquiring these companies to offer innovative products and services to customers.
There may also be a greater emphasis on financial education and financial wellness, as well as the integration of new technologies such as artificial intelligence and blockchain. Finally, there will be an increasing importance of sustainability and environmental concerns that may lead to a greater focus on sustainable finance and socially responsible investment options. Overall, the future of retail banking is likely to be marked by greater competition, innovation, and customer-centricity.
What are the biggest challenges in banking?
ChatGPT chatbot: The biggest challenges in retail banking today include:
- The rise of fintech companies: Fintech companies, which use technology to offer financial services, are increasingly competing with traditional banks for customers. This has put pressure on banks to innovate and improve the customer experience in order to remain competitive.
- Regulation and compliance: Retail banks must navigate a complex regulatory environment in order to operate, which can be a significant challenge. This includes complying with laws and regulations designed to protect consumers and ensure the stability of the financial system.
- Cybersecurity: As more financial transactions are conducted online, the risk of cyberattacks and data breaches has increased. This has made it necessary for banks to invest in robust cybersecurity measures to protect their customers and their own operations.
- Managing costs: Retail banks face pressure to keep costs down in order to remain profitable. This can be challenging, especially in an environment of low interest rates and increasing competition.
- Meeting customer expectations: Customers today have higher expectations for the services and products offered by banks. This includes expectations for fast, convenient, and personalized services, as well as a seamless digital experience. Meeting these expectations can be a challenge for banks.
What are the biggest opportunities in banking?
ChatGPT chatbot: The biggest opportunities in retail banking include:
- Digital transformation: The increasing use of technology in the financial industry presents an opportunity for banks to improve the customer experience and increase efficiency through digital transformation. This includes the adoption of mobile and online banking services, as well as the use of artificial intelligence and other technologies to automate routine tasks and provide personalized experiences.
- Expanding into new markets: As the global economy continues to grow and evolve, there may be opportunities for retail banks to expand into new markets, both domestically and internationally. This could include offering new products and services, or entering into partnerships with other companies to reach new customers.
- Innovation: The retail banking industry is ripe for innovation, as customers are increasingly seeking new and improved financial products and services. Banks that are able to successfully innovate and offer unique and valuable solutions may be able to gain a competitive advantage.
- Meeting the needs of underbanked populations: There are still many individuals and communities around the world that do not have access to basic financial services, such as banking accounts and loans. Retail banks have an opportunity to address this need by providing products and services that meet the unique needs of these populations.
- Partnerships and collaborations: The retail banking industry is becoming increasingly interconnected, with banks partnering and collaborating with other companies in the financial industry and beyond. These partnerships and collaborations can provide opportunities for banks to access new technologies, enter new markets, and offer more comprehensive solutions to customers.
Will solutions like ChatGPT replace humans?
ChatGPT chatbot: It is unlikely that solutions like me will completely replace humans. While ChatGPT and other large language models can perform many tasks that are typically associated with humans, such as answering questions and generating text, we are not capable of replacing human creativity, intuition, and empathy.
ChatGPT and other large language models are also not able to learn and adapt to new situations in the same way that humans can. Instead of replacing humans, ChatGPT and other large language models are more likely to augment human abilities and help us to perform tasks more efficiently.