This article “Risk Parity Portfolio” was written by Sergey Okun – Senior Financial Analyst at I Know First, Ph.D. in Economics.

• The risk parity portfolio technique enables us to identify optimal asset weights in the portfolio so that the contribution of each asset toward the total portfolio risk is equal.
• I Know First provides daily market forecasts for a broad range of financial assets for six investment horizons from 3-day to 1-year which help to identify the most promising financial assets according to the AI algorithm.
• We can build a portfolio based on the IKF AI algorithm, and construct the risk parity portfolio where each asset has the same risk contribution rate to the total portfolio risk.

The investment process consists of two broad tasks. One task is security and market analysis, by which we select assets, and the other task is the formation of an optimal portfolio of assets. I Know First provides daily market forecasts for a broad range of financial assets for six investment horizons from 3-day to 1-year which help to identify the most promising financial assets according to the AI algorithm. Below, we can observe the performance of the prediction of the Madicine package which was sent to our clients (you can access our forecast packages here). The forecast performance below is based on the assumption of an equal-weighted portfolio. The equal-weighted portfolio method could be not suitable for all investors because of the level of risk they are ready to hold. For example, there could be a very risky asset in a potential portfolio which makes the portfolio as a whole not suitable for an investor in terms of risk. In this case, it makes sense to consider the idea of the risk parity portfolio.

Package Name: Medicine Stocks
Recommended Positions: Long
Forecast Length: 1 Year (5/10/22 – 5/10/23)
I Know First Average: 14.25%

The risk parity portfolio technique enables us to identify optimal asset weights in the portfolio so that the contribution of each asset toward the total portfolio risk is equal. So, let us use stocks that were recommended by the IKF algorithm, and find stock weights based on risk parity. In our analysis, we use stock returns data from May 9^th, 2018, to May 9^th, 2022 (so that we are able to open positions on the next day according to the IKF algorithmic advice). Below, we can notice the covariance matrix for the stocks.

The portfolio variance is estimated by the following equation according to matrix multiplication rules.

According to equation 1, the portfolio variance is 0.0767, which corresponds to a volatility of 27.69%. Stocks contribute different levels of risk to a portfolio. For example, we should expect that adding utility stocks will contribute less risk to our portfolio than adding technology or energy stocks. Equation 2 enables us to estimate the risk contribution of stocks to a portfolio based on their weights.

We can notice from Table 2 that CLDX provides the highest risk contribution of 17.44% and LLY provides the lowest risk contribution of 5.45% to the equal-weighted portfolio.

Now we can build the risk parity portfolio by finding such weights in our portfolio where all stocks have the same risk contribution of 10%. In a technical meaning, we need to minimize the sum of the absolute deviation of each stock risk contribution to 10% (there are 10 stocks and each of them should contribute 10% of the risk to the portfolio).

Table 3 provides the outcome of the risk parity portfolio. It should be noticed that all stocks except LLY have a rate of 10% while LLY has a rate of 2.74%. Ideally, the rate of LLY has to be 10% when the minimum sum of deviations of all stocks is 0. However, in our case, the minimum sum of deviations of all stocks is 7.26%, which can be attached to the LLY stock rate of 2.74% in our portfolio. Overall, we can select stocks for a portfolio based on the IKF AI algorithm, and construct a risk parity portfolio, instead of using the equal-weighted method, where each asset has the same risk contribution rate to the total portfolio risk. That decreases portfolio sensitivity to failure in one stock because the risk exposure in this stock is the same as for other stocks in our portfolio.

Investment with I Know First

The I Know First predictive algorithm is a successful attempt to discover the rules of the market that enable us to make accurate stock market forecasts. Taking advantage of artificial intelligence and machine learning and using insights into chaos theory and self-similarity (the fractals), the algorithmic system is able to predict the behavior of over 13,500 markets. The key principle of the algorithm lies in the fact that a stock’s price is a function of many factors interacting non-linearly. Therefore, it is advantageous to use elements of artificial neural networks and genetic algorithms. How does it work? At first, an analysis of inputs is performed, ranking them according to their significance in predicting the target stock price. Then multiple models are created and tested utilizing 15 years of historical data. Only the best-performing models are kept while the rest are rejected. Models are refined every day, as new data becomes available. As the algorithm is purely empirical and self-learning, there is no human bias in the models and the market forecast system adapts to the new reality every day while still following general historical rules.

I Know First has used algorithmic outputs to provide an investment strategy for institutional investors. Below you can see the investment result of our S&P 500 Stocks package which was recommended to our clients for the period from January 1^st, 2020 to April 19^th, 2023 (you can access our forecast packages here).

The investment strategy that was recommended by I Know First accumulated a return of 80.29%, which exceeded the S&P 500 return by 51.69%.

Conclusion

The investment process consists of two broad tasks. One task is security and market analysis, by which we select assets, and the other task is the formation of an optimal portfolio of assets. The risk parity portfolio technique enables us to identify optimal asset weights in the portfolio so that the contribution of each asset toward the total portfolio risk is equal. We can build a portfolio based on the IKF AI algorithm, and construct the risk parity portfolio, instead of using the equal-weighted method, where each asset has the same risk contribution rate to the total portfolio risk. That decreases portfolio sensitivity to failure in one stock because the risk exposure in this stock is the same as for other stocks in our portfolio.

To subscribe today click here.

Please note-for trading decisions use the most recent forecast.