CONTRIBUTORS
Deep Ratna Srivastav
Chief AI Officer
Franklin Templeton Technology
Anand Radhakrishnan
Head of Digital Products
FTT AI & Digital Transformation
Vaneet Chadha, CFA
Portfolio Manager
Preview
When introduced to something new and innovative, people tend to interpret the new idea using ideas with which they’re already familiar. This is true of our Goals Optimization Engine in that people often assume the probability score generated by GOE is calculated using a Monte Carlo simulation. That’s understandable because the result of a Monte Carlo simulation is also a probability score, stated as a percentage of likelihood. However, GOE does not use Monte Carlo because Monte Carlo is not well suited to GOE’s mission of determining the appropriate mix of assets to hold at a given point in time.
In fact, if one were to use Monte Carlo as the calculation method inside GOE, it could take anywhere from several hours to literally millions of years to produce an answer. Instead, GOE uses a method known as dynamic programming, which can produce a result in seconds while still considering millions of possible outcomes across the time frame of a particular investment goal.
In this paper, we explain the use of dynamic programming within the Goals Optimization Engine (GOE®). In doing so, we will contrast the dynamic programming methodology with Monte Carlo analysis, a staple among modern financial planning tools. We also look at:
- GOE asking a question only dynamic programming can answer.
- Dynamic programming can work better, faster—and backwards.
- Managing the portfolio in “forward time” as gains or losses occur.
Readers interested in a broader understanding of GOE and goals-based wealth management should also read our other paper entitled “The missing link: Connecting goals-based wealth management to investing.”
WHAT ARE THE RISKS?
The views expressed are those of the investment manager and the comments, opinions and analyses are rendered as of the publication date and may change without notice. The underlying assumptions and these views are subject to change based on market and other conditions and may differ from other portfolio managers or of the firm as a whole. The information provided in this material is not intended as a complete analysis of every material fact regarding any country, region or market. There is no assurance that any prediction, projection or forecast on the economy, stock market, bond market or the economic trends of the markets will be realized. Probabilities predict the chance of an event and are only current as of the date indicated. This is no assurance that probabilities of targets or expectations will be achieved. The value of investments and the income from them can go down as well as up and you may not get back the full amount that you invested. Past performance is not necessarily indicative nor a guarantee of future performance. All investments involve risks, including possible loss of principal.
Hypothetical performance results may have many inherent risks. One of the limitations of hypothetical performance is that they are constructed with the benefit of hindsight. Alternative simulations, techniques, modeling or assumptions might produce significantly different results. Actual results will vary, perhaps materially, from the hypothetical results presented in this document. No representation is being made that any account will, or is likely to, achieve profits or losses similar to those described here.