Correspondence 0001592900-24-000705 from EA Series Trust (CIK 0001592900)
EA Series Trust (CIK 0001592900)
Date: May 6, 2024 · CIK: 0001592900 · Accession: 0001592900-24-000705
AI Filing Summary & Sentiment
File numbers found in text: 333-195493, 811-22961
Letter
Washington, DC 20549 Post-Effective Amendment No. 325 to the Registration Statement on Form N-1A (the “Amendment”) File Nos.: 333-195493 and 811-22961 Draco Evolution AI ETF
RE: EA Series Trust (the "Trust")
Dear Ms. Rossotto:
This correspondence responds to comments to the Trust received by the undersigned from the staff of the U.S. Securities and Exchange Commission (the “Staff” of the “Commission”) with respect to the Amendment relating to the Draco Evolution AI ETF (the “Fund”), a proposed new series of the Trust. For your convenience, the comments have been reproduced with responses following each comment. Capitalized terms not otherwise defined have the same meaning as in the Amendment.
1.Comment: Please explain why the reference to “AI” in the name of the Fund does not invoke Rule 35d-1 and the requirement to adopt an 80% investment policy.
Response: The reference to “AI” in the name of the Fund does not suggest the Fund focuses its investments in a particular type of investment or investments, a particular industry or group of industries, or whose issuers have particular characteristics. The use of “AI” in the name is simply a reference to the Sub-Adviser’s AI based investment model that will be used to guide investment selection for the Fund. The Fund’s use of “AI” is similar to how other funds include “fundamental” in their names.
2.Comment: Confirm that “Other Expenses” in Annual Operating Expense Table includes expenses associated with the Fund’s short selling.
Response: The Fund has revised its investment strategy discussion to remove references to the Fund short selling a security. Further, the Fund confirms that “Other Expenses” represents the Fund’s estimate of such expenses.
3.Comment: Please complete the Fund’s fee table and example and provide a copy to the Staff for review prior to the Fund’s effective date.
Response: The Fund has attached the Fund’s fee table and example to this correspondence. See Exhibit A.
4.Comment: Provide additional details in correspondences on how the proprietary AI model was developed for the investment process including:
•A discussion of signal to noise ratio and interpretability factors;
•The types of data inputs entered;
•The types of signals or output received;
•How is the output unbiased;
•How is the data validated for accuracy and reliability and who performs the validation;
•What specific outputs were considered;
•Any limitations on the use of the AI technology and the extent to which a portfolio manager will override the AI signals
11300 Tomahawk Creek Pkwy, Suite 310 ● Leawood, KS 66211
Practus, LLP ● Practus.com
Provide additional disclosure in the prospectus regarding the following:
•The use of incomplete data or erroneous data
•Potential for changes in relationships for data sets that could result in less useful outcomes or recommendations and/or potential for loss due to coding or logic errors and malware or other potential technology degradation associated with the use of technology.
Response: The Sub-Adviser to the Fund provides the following information in response to the comments regarding its AI model.
•The signal-to-noise ratio (SNR) quantifies the quality of information in a system by comparing the strength of the useful signal (relevant information) to the level of background noise (irrelevant information). The higher the SNR the better the AI model is in distinguishing relevant information from irrelevant information, resulting in more robust predictions. In analyzing the level of noise present in the strategy, the Sub-Adviser measures, such things as, the volatility of returns, calculating standard deviations or it may use other statistical techniques to quantify the randomness or unpredictability of the Fund’s investment strategy. For example, calculating the standard deviation of returns over a certain period provides an estimate of the volatility or noise level in the strategy. The Sub-Adviser then calculates the Sharpe ratio (return/volatility>1) to assess the quality of the predictions.
To strengthen the SNR, the Sub-Adviser will value and focus on Interpretability, which refers to the degree to which a trading strategy's decisions and actions can be understood and explained by humans, especially in economic logic, by building the AI model based on such methods like Tobin Q and SHAP. The Sub-Adviser uses methods like Tobin Q to determine the overall value of the market. Tobin Q or the Q ratio equals the market value of the market divided by its replacement cost. The Q ratio expresses the relationship between market valuation and intrinsic value – it provides the Sub-Adviser with an estimate of whether the market is overvalued or undervalued. In addition, the Sub-Adviser determines the SHAP value for each feature of its AI model to determine the contribution (importance) of each feature to the final prediction. SHAP values add up to the difference between the expected model output and the actual output for a given input. This provides the Sub-Adviser with an accurate and local interpretation of the AI model’s prediction for a given input. The SHAP values provide a consistent and objective way to gain insights into how the AI model makes predictions and which features have the greatest influence on the predictions.
•The Sub-Adviser’s model is divided into two parts: the AI model and the quantitative model. The AI model's inputs are based on stock prices, trading volumes, and proprietary indicators while the inputs for the quantitative model encompass more macroeconomic data, such as average weekly hours worked, applications for unemployment insurance, new orders for consumer goods and materials, new orders for capital goods, new building permits, the spread between long and short interest rates, the inflation-adjusted money supply, and average consumer expectations for business conditions. The Sub-Adviser combines the results from both the AI and quantitative models to make decisions for our portfolio.
•The AI model will categorize the market into bullish or bearish states, and every day before trading hours end, the trading system will indicate which state the market scenario is in, and then it will instruct the Fund to trade accordingly. The quantitate model will first generate or signal a macroeconomic prediction of either bullish or bearish. Depending on the strength of the bullish or bearish signal, the two models will classify the prediction as either macro-bull or macro-bear. Following this prediction, the AI model then generates the Fund’s portfolio allocation.
•The Sub-Adviser performs an out-of-the-sample test to ensure that the output is unbiased. In machine learning, an "out-of-sample test" refers to evaluating the performance of a trained model on data that it has not seen during the training process. During the training phase, a machine
learning model learns patterns and relationships in a dataset. However, the true test of its effectiveness is its ability to generalize to new, unseen data so the out-of-sample test involves feeding new data, which the model hasn't encountered before, to the trained model and assessing its performance. This test helps determine how well the model can make accurate predictions or classifications on data it wasn't trained on, providing insights into its real-world applicability and generalization capabilities.
•The Sub-Adviser validates the data every time they use it by comparing data from different sources. By using multiple sources for the data, the Sub-Adviser believes this reduces the likelihood of inaccurate or unreliable data. The Sub-Adviser’s data resources are from TD Ameritrade and Yahoo finance and to a lesser extent from Interactive Brokers. If the Sub-Adviser encounters data inconsistencies, it uses the following experience-based criteria to determine which data source to trust - whether there is any abnormal slippage in stock price information. For example, if the Sub-Adviser observes that the price of a stock at time “t” in minute “k’’ is 200, but at t+1 it abnormally drops below 100, and then returns to around 200 at t+2, this is a clear indication of an anomaly in the data provider’s database. The Sub-Adviser would not use data showing such abnormal price movements. If the data differences are very minor and do not affect the operation of our AI model, they are negligible and can be ignored.
•The output from the AI model is either a bearish or bullish signal. To evaluate the performance of the AI model, the Sub-Adviser considers the return, volatility, and Sharpe ratio of the Fund.
•The use of AI technology to assist in managing a fund is like any other fund where humans and technology are involved in the process. For example, humans either directly or through the use of technology can (among other things) make errors, misinterpret market data and/or allocate investments unsuccessfully. The use of AI technology in this process does not eliminate the possibility for errors or unsuccessful investment results. The Fund has included the following risk disclosures to inform shareholders that AI based strategies are no different from traditional strategies in that risk is involved with an investment in the Fund: AI Model Risk, Quantitative Security Selection Risk and Management Risk. The Fund believes these three risks coupled with the other Principal Risk provide shareholders with a robust risk discussion.
The Sub-Adviser’s AI model monitors for risk based on the underlying market activity of its holdings. As currently disclosed in the prospectus, the Sub-Adviser’s AI model monitors the Fund’s portfolio throughout the day and, if the Fund’s intraday drawdown exceeds 10% or when the Fund’s drawdown exceeds 20% from its all-time high the AI model will be paused, and the Sub-Adviser will be alerted. The Sub-Adviser will assess the situation and decide what steps, if any, to take as it relates to the portfolio.
•The Fund has expanded its risk disclosure to address the use of incomplete data or erroneous data and the potential for changes in relationships for data sets that could result in less useful outcomes or recommendations and/or potential for loss due to coding or logic errors and malware or other potential technology degradation associated with the use of technology.
5.Comment: In the Principal Investment Strategies section, please add information on the Fund’s investments in floating rate securities.
Response: The Fund will not invest directly in floating or variable rate securities, so it has removed Variable and Floating Rate Securities Risk from the prospectus. Floating rate securities risk is captured by Fixed Income Securities Risk.
6.Comment: In the Principal Investment Strategies section, please insert “junk bonds” next to the reference to high yield bonds.
Response: The Fund has inserted “junk bonds” next to high yield bonds in the Principal Investment Strategies section and as appropriate throughout the prospectus.
7.Comment: In the Principal Investment Strategies section, the Fund refers to investments in foreign securities. Confirm if that involves investments in emerging markets. If it does, insert risk disclosure regarding investments in emerging markets.
Response: The Fund’s exposure to foreign securities will be through its investments in other ETFs. Based on the Fund’s review of its ETF investment universe it does not believe emerging market investments will be principal to the investment strategy. Therefore, the Fund has not added emerging market risk to the Principal Risks section.
8.Comment: In the Principal Investment Strategies section, the Fund’s refers to investments in “one or more pooled vehicles”. Clarify if that includes investments in private funds. If it does add risk disclosure for such investments.
Response: The Fund will not invest in private funds. In addition, the Principal Investment Strategies section has been revised to remove the reference to “one or more pooled vehicles”.
9.Comment: In the Principal Investment Strategies section, please clarify what you mean by “other” in the following sentence:
“Consequently, the Fund’s investments in other exchange-traded vehicles may range from 0% to 100% of the Fund’s portfolio.”
Response: The Fund has removed the sentence in its entirety.
10.Comment: In the Principal Investment Strategies section, please clarify what you mean by “trained” in the following sentence:
“In making investment decisions, the Sub-Adviser’s AI-driven algorithms are trained to invest in asset classes that are expected to do well based on the algorithm’s market forecast.”
Response: Additional disclosure has been added to the Principal Investment Strategies section to further explain what is meant by “trained.” It is important to note the Sub-Adviser uses machine learning method for developing its models, In the context of machine learning, "training" refers to the process of teaching a machine learning model to make predictions or decisions based on input data. During training, the model is exposed to a dataset containing examples with known inputs and corresponding outputs (labels). The model adjusts its internal parameters through an optimization algorithm in order to minimize the difference between its predictions and the actual outputs in the training data. This process allows the model to learn patterns and relationships within the data, enabling it to make accurate predictions on new, unseen data. Training is a crucial step in the development of machine learning models and typically involves iteratively adjusting the model's parameters until it achieves satisfactory performance on the training dataset.
11.Comment: In correspondence, explain what makes the investment process employed by the Fund AI and not quantitative.
Response: The investment process involves AI and quantitative investing. The Sub-Adviser’s AI model is designed to improve itself through the use of quantitative analysis of data resources. As noted above, the AI model uses machine learning to inform its predictions. In the context of machine learning, "training" refers to the process of teaching a machine learning model to make predictions or decisions based on input data. During training, the model is exposed to a dataset containing examples with known inputs and corresponding outputs (labels). The model adjusts its model structure and input training data through an optimization algorithm in order to minimize the difference between its predictions and the actual outputs in the training data. This process allows the model to learn patterns and relationships within the data, enabling it to make accurate predictions on new, unseen data. Training is a crucial step in the development of machine learning models and typically involves iteratively adjusting the model's parameters until it achieves satisfactory performance on the training dataset.
12.Comment: In the Principal Investment Strategies section, should “predict current market conditions” be changed to “predict future market conditions”.
Response: The Fund has updated the sentence to state “future market conditions”.
13.Comment: Disclose in correspondence the data sources used by the model. Is the data provided by third parties? If yes, add risks regarding the possibility that the data could be inaccurate.
Response: The Sub-Adviser’s data resources are from TD Ameritrade and Yahoo finance and to a lesser extent from Interactive Brokers.
Yes, the Sub-Adviser has indicated that it relies on third-party data for its AI model. In order to reduce inaccurate data risk, the Sub-Adviser uses multiple sources for its data. Risk disclosure has been included in the Principal Investment Risks section of the prospectus regarding inaccurate data risk.
14.Comment: Add further explanat
Show Raw Text
CORRESP
1
filename1.htm
Document
May 6, 2024
Ms. Karen Rossotto
U.S. Securities and Exchange Commission
100 F Street, NE
Washington, DC 20549
RE: EA Series Trust (the "Trust")
Post-Effective Amendment No. 325 to the Registration Statement on Form N-1A (the “Amendment”) File Nos.: 333-195493 and 811-22961
Draco Evolution AI ETF
Dear Ms. Rossotto:
This correspondence responds to comments to the Trust received by the undersigned from the staff of the U.S. Securities and Exchange Commission (the “Staff” of the “Commission”) with respect to the Amendment relating to the Draco Evolution AI ETF (the “Fund”), a proposed new series of the Trust. For your convenience, the comments have been reproduced with responses following each comment. Capitalized terms not otherwise defined have the same meaning as in the Amendment.
1.Comment: Please explain why the reference to “AI” in the name of the Fund does not invoke Rule 35d-1 and the requirement to adopt an 80% investment policy.
Response: The reference to “AI” in the name of the Fund does not suggest the Fund focuses its investments in a particular type of investment or investments, a particular industry or group of industries, or whose issuers have particular characteristics. The use of “AI” in the name is simply a reference to the Sub-Adviser’s AI based investment model that will be used to guide investment selection for the Fund. The Fund’s use of “AI” is similar to how other funds include “fundamental” in their names.
2.Comment: Confirm that “Other Expenses” in Annual Operating Expense Table includes expenses associated with the Fund’s short selling.
Response: The Fund has revised its investment strategy discussion to remove references to the Fund short selling a security. Further, the Fund confirms that “Other Expenses” represents the Fund’s estimate of such expenses.
3.Comment: Please complete the Fund’s fee table and example and provide a copy to the Staff for review prior to the Fund’s effective date.
Response: The Fund has attached the Fund’s fee table and example to this correspondence. See Exhibit A.
4.Comment: Provide additional details in correspondences on how the proprietary AI model was developed for the investment process including:
•A discussion of signal to noise ratio and interpretability factors;
•The types of data inputs entered;
•The types of signals or output received;
•How is the output unbiased;
•How is the data validated for accuracy and reliability and who performs the validation;
•What specific outputs were considered;
•Any limitations on the use of the AI technology and the extent to which a portfolio manager will override the AI signals
11300 Tomahawk Creek Pkwy, Suite 310 ● Leawood, KS 66211
Practus, LLP ● Practus.com
Provide additional disclosure in the prospectus regarding the following:
•The use of incomplete data or erroneous data
•Potential for changes in relationships for data sets that could result in less useful outcomes or recommendations and/or potential for loss due to coding or logic errors and malware or other potential technology degradation associated with the use of technology.
Response: The Sub-Adviser to the Fund provides the following information in response to the comments regarding its AI model.
•The signal-to-noise ratio (SNR) quantifies the quality of information in a system by comparing the strength of the useful signal (relevant information) to the level of background noise (irrelevant information). The higher the SNR the better the AI model is in distinguishing relevant information from irrelevant information, resulting in more robust predictions. In analyzing the level of noise present in the strategy, the Sub-Adviser measures, such things as, the volatility of returns, calculating standard deviations or it may use other statistical techniques to quantify the randomness or unpredictability of the Fund’s investment strategy. For example, calculating the standard deviation of returns over a certain period provides an estimate of the volatility or noise level in the strategy. The Sub-Adviser then calculates the Sharpe ratio (return/volatility>1) to assess the quality of the predictions.
To strengthen the SNR, the Sub-Adviser will value and focus on Interpretability, which refers to the degree to which a trading strategy's decisions and actions can be understood and explained by humans, especially in economic logic, by building the AI model based on such methods like Tobin Q and SHAP. The Sub-Adviser uses methods like Tobin Q to determine the overall value of the market. Tobin Q or the Q ratio equals the market value of the market divided by its replacement cost. The Q ratio expresses the relationship between market valuation and intrinsic value – it provides the Sub-Adviser with an estimate of whether the market is overvalued or undervalued. In addition, the Sub-Adviser determines the SHAP value for each feature of its AI model to determine the contribution (importance) of each feature to the final prediction. SHAP values add up to the difference between the expected model output and the actual output for a given input. This provides the Sub-Adviser with an accurate and local interpretation of the AI model’s prediction for a given input. The SHAP values provide a consistent and objective way to gain insights into how the AI model makes predictions and which features have the greatest influence on the predictions.
•The Sub-Adviser’s model is divided into two parts: the AI model and the quantitative model. The AI model's inputs are based on stock prices, trading volumes, and proprietary indicators while the inputs for the quantitative model encompass more macroeconomic data, such as average weekly hours worked, applications for unemployment insurance, new orders for consumer goods and materials, new orders for capital goods, new building permits, the spread between long and short interest rates, the inflation-adjusted money supply, and average consumer expectations for business conditions. The Sub-Adviser combines the results from both the AI and quantitative models to make decisions for our portfolio.
•The AI model will categorize the market into bullish or bearish states, and every day before trading hours end, the trading system will indicate which state the market scenario is in, and then it will instruct the Fund to trade accordingly. The quantitate model will first generate or signal a macroeconomic prediction of either bullish or bearish. Depending on the strength of the bullish or bearish signal, the two models will classify the prediction as either macro-bull or macro-bear. Following this prediction, the AI model then generates the Fund’s portfolio allocation.
•The Sub-Adviser performs an out-of-the-sample test to ensure that the output is unbiased. In machine learning, an "out-of-sample test" refers to evaluating the performance of a trained model on data that it has not seen during the training process. During the training phase, a machine
2
learning model learns patterns and relationships in a dataset. However, the true test of its effectiveness is its ability to generalize to new, unseen data so the out-of-sample test involves feeding new data, which the model hasn't encountered before, to the trained model and assessing its performance. This test helps determine how well the model can make accurate predictions or classifications on data it wasn't trained on, providing insights into its real-world applicability and generalization capabilities.
•The Sub-Adviser validates the data every time they use it by comparing data from different sources. By using multiple sources for the data, the Sub-Adviser believes this reduces the likelihood of inaccurate or unreliable data. The Sub-Adviser’s data resources are from TD Ameritrade and Yahoo finance and to a lesser extent from Interactive Brokers. If the Sub-Adviser encounters data inconsistencies, it uses the following experience-based criteria to determine which data source to trust - whether there is any abnormal slippage in stock price information. For example, if the Sub-Adviser observes that the price of a stock at time “t” in minute “k’’ is 200, but at t+1 it abnormally drops below 100, and then returns to around 200 at t+2, this is a clear indication of an anomaly in the data provider’s database. The Sub-Adviser would not use data showing such abnormal price movements. If the data differences are very minor and do not affect the operation of our AI model, they are negligible and can be ignored.
•The output from the AI model is either a bearish or bullish signal. To evaluate the performance of the AI model, the Sub-Adviser considers the return, volatility, and Sharpe ratio of the Fund.
•The use of AI technology to assist in managing a fund is like any other fund where humans and technology are involved in the process. For example, humans either directly or through the use of technology can (among other things) make errors, misinterpret market data and/or allocate investments unsuccessfully. The use of AI technology in this process does not eliminate the possibility for errors or unsuccessful investment results. The Fund has included the following risk disclosures to inform shareholders that AI based strategies are no different from traditional strategies in that risk is involved with an investment in the Fund: AI Model Risk, Quantitative Security Selection Risk and Management Risk. The Fund believes these three risks coupled with the other Principal Risk provide shareholders with a robust risk discussion.
The Sub-Adviser’s AI model monitors for risk based on the underlying market activity of its holdings. As currently disclosed in the prospectus, the Sub-Adviser’s AI model monitors the Fund’s portfolio throughout the day and, if the Fund’s intraday drawdown exceeds 10% or when the Fund’s drawdown exceeds 20% from its all-time high the AI model will be paused, and the Sub-Adviser will be alerted. The Sub-Adviser will assess the situation and decide what steps, if any, to take as it relates to the portfolio.
•The Fund has expanded its risk disclosure to address the use of incomplete data or erroneous data and the potential for changes in relationships for data sets that could result in less useful outcomes or recommendations and/or potential for loss due to coding or logic errors and malware or other potential technology degradation associated with the use of technology.
5.Comment: In the Principal Investment Strategies section, please add information on the Fund’s investments in floating rate securities.
Response: The Fund will not invest directly in floating or variable rate securities, so it has removed Variable and Floating Rate Securities Risk from the prospectus. Floating rate securities risk is captured by Fixed Income Securities Risk.
6.Comment: In the Principal Investment Strategies section, please insert “junk bonds” next to the reference to high yield bonds.
Response: The Fund has inserted “junk bonds” next to high yield bonds in the Principal Investment Strategies section and as appropriate throughout the prospectus.
3
7.Comment: In the Principal Investment Strategies section, the Fund refers to investments in foreign securities. Confirm if that involves investments in emerging markets. If it does, insert risk disclosure regarding investments in emerging markets.
Response: The Fund’s exposure to foreign securities will be through its investments in other ETFs. Based on the Fund’s review of its ETF investment universe it does not believe emerging market investments will be principal to the investment strategy. Therefore, the Fund has not added emerging market risk to the Principal Risks section.
8.Comment: In the Principal Investment Strategies section, the Fund’s refers to investments in “one or more pooled vehicles”. Clarify if that includes investments in private funds. If it does add risk disclosure for such investments.
Response: The Fund will not invest in private funds. In addition, the Principal Investment Strategies section has been revised to remove the reference to “one or more pooled vehicles”.
9.Comment: In the Principal Investment Strategies section, please clarify what you mean by “other” in the following sentence:
“Consequently, the Fund’s investments in other exchange-traded vehicles may range from 0% to 100% of the Fund’s portfolio.”
Response: The Fund has removed the sentence in its entirety.
10.Comment: In the Principal Investment Strategies section, please clarify what you mean by “trained” in the following sentence:
“In making investment decisions, the Sub-Adviser’s AI-driven algorithms are trained to invest in asset classes that are expected to do well based on the algorithm’s market forecast.”
Response: Additional disclosure has been added to the Principal Investment Strategies section to further explain what is meant by “trained.” It is important to note the Sub-Adviser uses machine learning method for developing its models, In the context of machine learning, "training" refers to the process of teaching a machine learning model to make predictions or decisions based on input data. During training, the model is exposed to a dataset containing examples with known inputs and corresponding outputs (labels). The model adjusts its internal parameters through an optimization algorithm in order to minimize the difference between its predictions and the actual outputs in the training data. This process allows the model to learn patterns and relationships within the data, enabling it to make accurate predictions on new, unseen data. Training is a crucial step in the development of machine learning models and typically involves iteratively adjusting the model's parameters until it achieves satisfactory performance on the training dataset.
11.Comment: In correspondence, explain what makes the investment process employed by the Fund AI and not quantitative.
Response: The investment process involves AI and quantitative investing. The Sub-Adviser’s AI model is designed to improve itself through the use of quantitative analysis of data resources. As noted above, the AI model uses machine learning to inform its predictions. In the context of machine learning, "training" refers to the process of teaching a machine learning model to make predictions or decisions based on input data. During training, the model is exposed to a dataset containing examples with known inputs and corresponding outputs (labels). The model adjusts its model structure and input training data through an optimization algorithm in order to minimize the difference between its predictions and the actual outputs in the training data. This process allows the model to learn patterns and relationships within the data, enabling it to make accurate predictions on new, unseen data. Training is a crucial step in the development of machine learning models and typically involves iteratively adjusting the model's parameters until it achieves satisfactory performance on the training dataset.
4
12.Comment: In the Principal Investment Strategies section, should “predict current market conditions” be changed to “predict future market conditions”.
Response: The Fund has updated the sentence to state “future market conditions”.
13.Comment: Disclose in correspondence the data sources used by the model. Is the data provided by third parties? If yes, add risks regarding the possibility that the data could be inaccurate.
Response: The Sub-Adviser’s data resources are from TD Ameritrade and Yahoo finance and to a lesser extent from Interactive Brokers.
Yes, the Sub-Adviser has indicated that it relies on third-party data for its AI model. In order to reduce inaccurate data risk, the Sub-Adviser uses multiple sources for its data. Risk disclosure has been included in the Principal Investment Risks section of the prospectus regarding inaccurate data risk.
14.Comment: Add further explanat