Outlook: ADAIRS LIMITED assigned short-term Ba1 & long-term Ba1 estimated rating.
Dominant Strategy : Sell
Time series to forecast n: 28 Dec 2022 for (n+16 weeks)
Methodology : Statistical Inference (ML)

## Abstract

The aim of this study is to evaluate the effectiveness of using external indicators, such as commodity prices and currency exchange rates, in predicting movements. The performance of each technique is evaluated using different domain specific metrics. A comprehensive evaluation procedure is described, involving the use of trading simulations to assess the practical value of predictive models, and comparison with simple benchmarks that respond to underlying market growth.(Kim, K.J. and Han, I., 2000. Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index. Expert systems with Applications, 19(2), pp.125-132.) We evaluate ADAIRS LIMITED prediction models with Statistical Inference (ML) and Chi-Square1,2,3,4 and conclude that the ADH stock is predictable in the short/long term. According to price forecasts for (n+16 weeks) period, the dominant strategy among neural network is: Sell

## Key Points

1. What is the use of Markov decision process?
2. Technical Analysis with Algorithmic Trading
3. Decision Making

## ADH Target Price Prediction Modeling Methodology

We consider ADAIRS LIMITED Decision Process with Statistical Inference (ML) where A is the set of discrete actions of ADH 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(Chi-Square)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(Statistical Inference (ML)) X S(n):→ (n+16 weeks) $R=\left(\begin{array}{ccc}1& 0& 0\\ 0& 1& 0\\ 0& 0& 1\end{array}\right)$

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
Time series to forecast n: 28 Dec 2022 for (n+16 weeks)

According to price forecasts for (n+16 weeks) period, the dominant strategy among neural network is: Sell

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 (Grey to Black): *Technical Analysis%

1. There is a rebuttable presumption that unless inflation risk is contractually specified, it is not separately identifiable and reliably measurable and hence cannot be designated as a risk component of a financial instrument. However, in limited cases, it is possible to identify a risk component for inflation risk that is separately identifiable and reliably measurable because of the particular circumstances of the inflation environment and the relevant debt market
2. Accordingly the date of the modification shall be treated as the date of initial recognition of that financial asset when applying the impairment requirements to the modified financial asset. This typically means measuring the loss allowance at an amount equal to 12-month expected credit losses until the requirements for the recognition of lifetime expected credit losses in paragraph 5.5.3 are met. However, in some unusual circumstances following a modification that results in derecognition of the original financial asset, there may be evidence that the modified financial asset is credit-impaired at initial recognition, and thus, the financial asset should be recognised as an originated credit-impaired financial asset. This might occur, for example, in a situation in which there was a substantial modification of a distressed asset that resulted in the derecognition of the original financial asset. In such a case, it may be possible for the modification to result in a new financial asset which is credit-impaired at initial recognition.
3. For the purposes of applying the requirements in paragraphs 5.7.7 and 5.7.8, an accounting mismatch is not caused solely by the measurement method that an entity uses to determine the effects of changes in a liability's credit risk. An accounting mismatch in profit or loss would arise only when the effects of changes in the liability's credit risk (as defined in IFRS 7) are expected to be offset by changes in the fair value of another financial instrument. A mismatch that arises solely as a result of the measurement method (ie because an entity does not isolate changes in a liability's credit risk from some other changes in its fair value) does not affect the determination required by paragraphs 5.7.7 and 5.7.8. For example, an entity may not isolate changes in a liability's credit risk from changes in liquidity risk. If the entity presents the combined effect of both factors in other comprehensive income, a mismatch may occur because changes in liquidity risk may be included in the fair value measurement of the entity's financial assets and the entire fair value change of those assets is presented in profit or loss. However, such a mismatch is caused by measurement imprecision, not the offsetting relationship described in paragraph B5.7.6 and, therefore, does not affect the determination required by paragraphs 5.7.7 and 5.7.8.
4. The decision of an entity to designate a financial asset or financial liability as at fair value through profit or loss is similar to an accounting policy choice (although, unlike an accounting policy choice, it is not required to be applied consistently to all similar transactions). When an entity has such a choice, paragraph 14(b) of IAS 8 requires the chosen policy to result in the financial statements providing reliable and more relevant information about the effects of transactions, other events and conditions on the entity's financial position, financial performance or cash flows. For example, in the case of designation of a financial liability as at fair value through profit or loss, paragraph 4.2.2 sets out the two circumstances when the requirement for more relevant information will be met. Accordingly, to choose such designation in accordance with paragraph 4.2.2, the entity needs to demonstrate that it falls within one (or both) of these two circumstances.

*International Financial Reporting Standards (IFRS) adjustment process involves reviewing the company's financial statements and identifying any differences between the company's current accounting practices and the requirements of the IFRS. If there are any such differences, neural network makes adjustments to financial statements to bring them into compliance with the IFRS.

## Conclusions

ADAIRS LIMITED assigned short-term Ba1 & long-term Ba1 estimated rating. We evaluate the prediction models Statistical Inference (ML) with Chi-Square1,2,3,4 and conclude that the ADH stock is predictable in the short/long term. According to price forecasts for (n+16 weeks) period, the dominant strategy among neural network is: Sell

Rating Short-Term Long-Term Senior
Outlook*Ba1Ba1
Income StatementB1Baa2
Balance SheetCBaa2
Leverage RatiosB1C
Cash FlowBaa2Ba2
Rates of Return and ProfitabilityB1Baa2

*Financial analysis is the process of evaluating a company's financial performance and position by neural network. It involves reviewing the company's financial statements, including the balance sheet, income statement, and cash flow statement, as well as other financial reports and documents.
How does neural network examine financial reports and understand financial state of the company?

### Prediction Confidence Score

Trust metric by Neural Network: 83 out of 100 with 629 signals.

## References

1. M. J. Hausknecht and P. Stone. Deep recurrent Q-learning for partially observable MDPs. CoRR, abs/1507.06527, 2015
2. E. Collins. Using Markov decision processes to optimize a nonlinear functional of the final distribution, with manufacturing applications. In Stochastic Modelling in Innovative Manufacturing, pages 30–45. Springer, 1997
3. Çetinkaya, A., Zhang, Y.Z., Hao, Y.M. and Ma, X.Y., When to Sell and When to Hold AQN Stock. AC Investment Research Journal, 101(3).
4. Lai TL, Robbins H. 1985. Asymptotically efficient adaptive allocation rules. Adv. Appl. Math. 6:4–22
5. Kallus N. 2017. Balanced policy evaluation and learning. arXiv:1705.07384 [stat.ML]
6. Çetinkaya, A., Zhang, Y.Z., Hao, Y.M. and Ma, X.Y., When to Sell and When to Hold AQN Stock. AC Investment Research Journal, 101(3).
7. Bastani H, Bayati M. 2015. Online decision-making with high-dimensional covariates. Work. Pap., Univ. Penn./ Stanford Grad. School Bus., Philadelphia/Stanford, CA