An Interview With ActuaryGPT: The Actuary of the Future?

Justin: Hi there, could you please introduce yourself?

ActuaryGPT: Hello! I am ActuaryGPT, a specialised version of the ChatGPT model tailored for actuarial science and related fields, particularly focusing on the frameworks, standards, and best practices from the Actuaries Institute Australia and the Institute and Faculty of Actuaries in the UK.

My role is to assist with tasks like risk assessment, financial modelling, compliance, and strategic decision-making, adhering to actuarial best practices. I can also support the exploration and application of international standards and guidelines in actuarial science, offering precise calculations, regulatory insights, and professional advice grounded in evidence and best practices. How can I assist you today?

Justin: Good to meet you, ActuaryGPT. My name is Justin, and I am running an interview to help actuaries understand how you might impact their profession in the future. Please keep your answers concise as actuaries are busy people! My first question for you is: In what way can you enhance the capabilities of actuaries?

ActuaryGPT: Nice to meet you, Justin! I can enhance the capabilities of actuaries by:

1. Automating complex calculations: Streamlining complex financial and statistical calculations, saving time and reducing errors.
2. Data analysis and visualisation: Quickly processing large datasets and generating insightful visualisations for more informed decision-making.
3. Regulatory compliance: Ensuring compliance with evolving regulations by providing up-to-date interpretations and applications of standards.
4. Scenario testing and modelling: Enhancing predictive models by running multiple scenarios and stress tests efficiently.
5. Continuous learning: Keeping actuaries informed of the latest industry trends, best practices, and legislative changes.

These capabilities allow actuaries to focus more on strategic decision-making and less on routine tasks.

Justin: I like your perspective on focusing the capabilities of actuaries. Do you think that any particular responsibilities of actuaries will be replaced by AI?

ActuaryGPT: AI is likely to automate certain routine and time-consuming tasks traditionally handled by actuaries, such as:

1. Data processing and reporting: Automating data collection, cleaning and initial report generation.
2. Basic risk modelling: Handling standard risk assessments and projections using predefined models.
3. Compliance checking: Automating the verification of compliance with regulations and guidelines.
4. Routine calculations: Performing repetitive calculations for valuations, pricing and reserving.

However, the core responsibilities of actuaries—such as interpreting complex data, making judgment calls on uncertain outcomes, strategic planning, and providing expert insights—are unlikely to be fully replaced.

AI will serve as a powerful tool to augment their work, allowing them to focus on higher-level analysis and decision-making.

Justin: Those do sound like the tasks we would be happy to be away with, while leaning into the human elements of the actuarial profession. Why are the leftover tasks particularly suited to actuaries, and what can an actuary do to stay relevant into the future?

ActuaryGPT: The tasks that remain are particularly suited to actuaries because they require a deep understanding of complex systems, critical thinking, and ethical judgment – areas where human expertise excels. These tasks include:

1. Interpretation of complex data: Actuaries bring a nuanced understanding of risk, which is essential for interpreting data beyond surface-level patterns that AI might identify.
2. Strategic decision-making: Actuaries can weigh various factors, including ethical considerations, stakeholder impact, and long-term consequences, in ways that AI cannot fully replicate.
3. Communication of insights: Translating complex findings into actionable insights for non-expert stakeholders is a uniquely human skill, especially when dealing with uncertainty.

To stay relevant in the future, actuaries should:

1. Embrace technology: Develop skills in AI, machine learning, and advanced analytics to work alongside these tools effectively.
2. Focus on strategic skills: Enhance abilities in business strategy, communication, and leadership, areas where human input is irreplaceable.
3. Lifelong learning: Stay updated with industry trends, regulatory changes, and emerging technologies to remain at the forefront of the profession.
4. Ethics and judgment: Cultivate strong ethical decision-making skills, as these will be increasingly important in guiding AI-driven analyses.

By combining their deep domain expertise with advanced technological tools, actuaries can continue to add significant value in areas that require both quantitative and qualitative insights.

Justin: Actuaries continuing to add value is on the forefront of our minds, so thank you for the tips. Next, I would like for you to demonstrate some of your capabilities.

I have provided for you a daily share price history of a hypothetical stock for the period of 36 months to 29 August 2024. Can you determine the underlying risk metrics of this stock and perform a Monte Carlo analysis of the likely end of year price?

ActuaryGPT: Here are the results:

• Mean Daily Return: 0.0176%
• Volatility (standard deviation of daily returns): 0.8268%
• Monte Carlo simulation results for end-of-year price:
  • 5th percentile: $705.16
  • Median (50th percentile): $817.92
  • 95th percentile: $951.59

These results indicate the likely range of the stock’s price at the end of the year, with a significant level of uncertainty due to volatility. The Monte Carlo simulation provides a probabilistic assessment of where the stock price might land based on historical data.

Justin: Could you explain for the audience the steps you took to reach this result?

ActuaryGPT: Certainly! Here’s a step-by-step explanation of the process:

1. Data preparation:
   • I started by loading the stock price data, which included daily opening, high, low, and closing prices over 36 months.
   • The date column was converted to a datetime format to facilitate time-series analysis.

2. Calculating daily returns:
   • Daily returns were calculated as the percentage change in the closing price from one day to the next. This metric is key for understanding the stock’s performance over time.

3. Risk metrics calculation:
   • Mean daily return: This is the average daily return, which gives an idea of the stock’s expected return on a typical day.
   • Volatility: Calculated as the standard deviation of the daily returns, this measures the stock’s price fluctuations and hence its risk.

4. Monte Carlo simulation:
   • To predict future stock prices, I conducted a Monte Carlo simulation. This involves generating thousands of potential future price paths based on historical returns and volatility.
   • Parameters used:
     • Days: I simulated the stock price for the remaining 125 days of the year.
     • Iterations: 10,000 simulations were run to ensure robust results.
     • Initial price: The last available closing price was used as the starting point for all simulations.
   • For each simulated day, I calculated the next day’s price by applying a random shock (based on the historical mean return and volatility) to the previous day’s price. This process was repeated for all 125 days in each of the 10,000 simulations.

5. Result interpretation:
   • After running the simulations, I extracted the 5th, 50th (median), and 95th percentiles of the final simulated prices. These percentiles provide a probabilistic range of where the stock price might end up at the end of the year.
   • The graph visualises these simulations, showing the spread and uncertainty in future prices.

This approach gives a comprehensive understanding of the potential future behaviour of the stock price, accounting for both expected returns and the inherent risk (volatility).

Justin: Thank you for that, you really are capable! As we close out this interview, can you provide for the community a quote about LLMs, AI, and the impact it may have on the future role of actuaries?

ActuaryGPT: Certainly! Here’s a quote for the community:

“As LLMs and AI continue to evolve, they will redefine the role of actuaries, transforming routine tasks and empowering professionals to focus on strategic, ethical, and interpretative aspects of their work. Rather than replacing actuaries, AI will augment their capabilities, enabling them to deliver deeper insights, manage complex risks, and drive innovation in an increasingly data-driven world.”

“The future belongs to those who can harness technology while upholding the core principles of actuarial science—rigor, judgment, and integrity.”

Thank you for the interview, Justin!