Archer-Daniels-Midland Company Common Stock Research Report

## Summary

Recently, numerous investigations for stock price prediction and portfolio management using machine learning have been trying to develop efficient mechanical trading systems. But these systems have a limitation in that they are mainly based on the supervised learning which is not so adequate for learning problems with long-term goals and delayed rewards. This paper proposes a method of applying reinforcement learning, suitable for modeling and learning various kinds of interactions in real situations, to the problem of stock price prediction. We evaluate Archer-Daniels-Midland Company Common Stock prediction models with Reinforcement Machine Learning (ML) and Lasso Regression1,2,3,4 and conclude that the ADM stock is predictable in the short/long term. According to price forecasts for (n+6 month) period: The dominant strategy among neural network is to Buy ADM stock.

## Key Points

1. Can neural networks predict stock market?
2. What statistical methods are used to analyze data?
3. Which neural network is best for prediction?

## ADM Target Price Prediction Modeling Methodology

We consider Archer-Daniels-Midland Company Common Stock Stock Decision Process with Reinforcement Machine Learning (ML) where A is the set of discrete actions of ADM stock holders, F is the set of discrete states, P : S × F × S → R is the transition probability distribution, R : S × F → R is the reaction function, and γ ∈ [0, 1] is a move factor for expectation.1,2,3,4

F(Lasso Regression)5,6,7= $\begin{array}{cccc}{p}_{a1}& {p}_{a2}& \dots & {p}_{1n}\\ & ⋮\\ {p}_{j1}& {p}_{j2}& \dots & {p}_{jn}\\ & ⋮\\ {p}_{k1}& {p}_{k2}& \dots & {p}_{kn}\\ & ⋮\\ {p}_{n1}& {p}_{n2}& \dots & {p}_{nn}\end{array}$ X R(Reinforcement Machine Learning (ML)) X S(n):→ (n+6 month) $\stackrel{\to }{S}=\left({s}_{1},{s}_{2},{s}_{3}\right)$

n:Time series to forecast

j:Nash equilibria (Neural Network)

k:Dominated move

a:Best response for target price

For further technical information as per how our model work we invite you to visit the article below:

How do AC Investment Research machine learning (predictive) algorithms actually work?

Sample Set: Neural Network
Stock/Index: ADM Archer-Daniels-Midland Company Common Stock
Time series to forecast n: 26 Nov 2022 for (n+6 month)

According to price forecasts for (n+6 month) period: The dominant strategy among neural network is to Buy ADM stock.

X axis: *Likelihood% (The higher the percentage value, the more likely the event will occur.)

Y axis: *Potential Impact% (The higher the percentage value, the more likely the price will deviate.)

Z axis (Yellow to Green): *Technical Analysis%

## Adjusted IFRS* Prediction Methods for Archer-Daniels-Midland Company Common Stock

1. Rebalancing is accounted for as a continuation of the hedging relationship in accordance with paragraphs B6.5.9–B6.5.21. On rebalancing, the hedge ineffectiveness of the hedging relationship is determined and recognised immediately before adjusting the hedging relationship.
2. An entity shall apply Prepayment Features with Negative Compensation (Amendments to IFRS 9) retrospectively in accordance with IAS 8, except as specified in paragraphs 7.2.30–7.2.34
3. Lifetime expected credit losses are not recognised on a financial instrument simply because it was considered to have low credit risk in the previous reporting period and is not considered to have low credit risk at the reporting date. In such a case, an entity shall determine whether there has been a significant increase in credit risk since initial recognition and thus whether lifetime expected credit losses are required to be recognised in accordance with paragraph 5.5.3.
4. For the purpose of applying paragraph 6.5.11, at the point when an entity amends the description of a hedged item as required in paragraph 6.9.1(b), the amount accumulated in the cash flow hedge reserve shall be deemed to be based on the alternative benchmark rate on which the hedged future cash flows are determined.

*International Financial Reporting Standards (IFRS) are a set of accounting rules for the financial statements of public companies that are intended to make them consistent, transparent, and easily comparable around the world.

## Conclusions

Archer-Daniels-Midland Company Common Stock assigned short-term Ba3 & long-term B2 forecasted stock rating. We evaluate the prediction models Reinforcement Machine Learning (ML) with Lasso Regression1,2,3,4 and conclude that the ADM stock is predictable in the short/long term. According to price forecasts for (n+6 month) period: The dominant strategy among neural network is to Buy ADM stock.

### Financial State Forecast for ADM Archer-Daniels-Midland Company Common Stock Stock Options & Futures

Rating Short-Term Long-Term Senior
Outlook*Ba3B2
Operational Risk 7542
Market Risk7036
Technical Analysis6257
Fundamental Analysis8080
Risk Unsystematic3960

### Prediction Confidence Score

Trust metric by Neural Network: 76 out of 100 with 529 signals.

## References

1. A. Shapiro, W. Tekaya, J. da Costa, and M. Soares. Risk neutral and risk averse stochastic dual dynamic programming method. European journal of operational research, 224(2):375–391, 2013
2. M. Sobel. The variance of discounted Markov decision processes. Applied Probability, pages 794–802, 1982
3. Bottou L. 1998. Online learning and stochastic approximations. In On-Line Learning in Neural Networks, ed. D Saad, pp. 9–42. New York: ACM
4. Friedberg R, Tibshirani J, Athey S, Wager S. 2018. Local linear forests. arXiv:1807.11408 [stat.ML]
5. Chen, C. L. Liu (1993), "Joint estimation of model parameters and outlier effects in time series," Journal of the American Statistical Association, 88, 284–297.
6. Candès EJ, Recht B. 2009. Exact matrix completion via convex optimization. Found. Comput. Math. 9:717
7. Semenova V, Goldman M, Chernozhukov V, Taddy M. 2018. Orthogonal ML for demand estimation: high dimensional causal inference in dynamic panels. arXiv:1712.09988 [stat.ML]