Portfolio Allocation System Using Monte Carlo Simulations

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing portfolio allocation systems fail to adequately address retirement risks such as longevity, inflation, sequence of returns, and excess withdrawal rates, as they primarily focus on risk tolerance and expected return without considering legacy and liquidity desires, especially when incorporating non-traditional assets like annuities.

Innovation Solution

A computerized method that creates a solution space of financial product combinations including traditional and non-traditional assets, using Monte Carlo simulations to optimize asset allocation based on investor-specific information like life expectancy, retirement objectives, and desired withdrawal rates, to maximize legacy and income potential while minimizing the risk of running out of money.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If traditional asset allocation models focusing on risk tolerance and expected return are used, then portfolio optimization is simplified, but retirement risks such as longevity, inflation, sequence of returns, and excess withdrawal rates are not adequately addressed

Engineering Contradiction:

Improveportfolio allocation model complexityVSAvoidretirement risk mitigation

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The patent segments the retirement portfolio into multiple asset classes (traditional assets, non-traditional assets, annuities, insurance products) and evaluates each segment's contribution to specific retirement risks. This segmentation allows the system to address multiple retirement risks simultaneously while maintaining manageable model complexity through modular analysis.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces new parameters beyond traditional risk tolerance and expected return, including life expectancy, inflation expectations, withdrawal rates, and legacy goals. These parameter changes enable the model to capture retirement-specific risks while using Monte Carlo simulation to handle the increased dimensionality without exponential complexity growth.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If non-traditional assets like annuities are incorporated into the portfolio, then retirement risk mitigation is improved, but the difficulty of detecting and measuring optimal allocation increases

Engineering Contradiction:

Improveretirement risk mitigationVSAvoidoptimal allocation determination

Core Design Contradiction:

ReliabilityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent implements feedback loops where Monte Carlo simulation results provide information about portfolio performance under various retirement scenarios. This feedback is used to iteratively adjust allocations of non-traditional assets, allowing the system to navigate the complexity of measuring optimal allocation while improving retirement risk mitigation through learned insights.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent introduces an intermediary computational layer (Monte Carlo simulation engine) that mediates between the complex inputs (multiple asset classes, retirement risks, investor preferences) and the output (optimal allocation). This intermediary handles the computational complexity of evaluating non-traditional assets by simulating thousands of retirement scenarios, making the measurement of optimal allocation tractable.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If Monte Carlo simulations are used to optimize asset allocation based on investor-specific information, then retirement planning accuracy is improved, but computational requirements and processing time increase

Engineering Contradiction:

Improveretirement planning accuracyVSAvoidcomputational processing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary actions by pre-calculating and storing key statistical parameters (mean returns, volatilities, correlations) for different asset classes before running Monte Carlo simulations. This preliminary preparation reduces the computational burden during actual retirement planning, allowing high measurement precision while minimizing processing time through efficient use of pre-computed data.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS10453140B2System and method for allocating traditional and non-traditional assets in an investment portfolio

Publication Date: 2019.10.22 NEW YORK LIFE INSURANCE CO

AI summary

A computerized method and system for allocating assets among a plurality of financial products for an investor portfolio includes calculating a solution space of financial vehicle combinations by assigning allocations to each financial vehicle in each financial vehicle combination and generating a set of simulations, for each of the vehicle combinations, of a value of the financial vehicle combination. The computerized method and system further includes receiving investor-specific information, the investor-specific information including a retirement objective. The method and system further includes selecting a set of financial vehicle combinations within the solution space based on the received investor-specific information; and allocating assets among the plurality of financial products based on the set of selected financial vehicle combinations and received investor-specific information.