CRESTCHIC PLC Research Report

## Summary

In this paper, we propose a robust and novel hybrid model for prediction of stock returns. The proposed model is constituted of two linear models: autoregressive moving average model, exponential smoothing model and a non-linear model: recurrent neural network. Training data for recurrent neural network is generated by a new regression model. Recurrent neural network produces satisfactory predictions as compared to linear models. With the goal to further improve the accuracy of predictions, the proposed hybrid prediction model merges predictions obtained from these three prediction based models. We evaluate CRESTCHIC PLC prediction models with Supervised Machine Learning (ML) and Pearson Correlation1,2,3,4 and conclude that the LON:LOAD stock is predictable in the short/long term. According to price forecasts for (n+8 weeks) period: The dominant strategy among neural network is to Sell LON:LOAD stock.

## Key Points

1. What statistical methods are used to analyze data?
2. Is Target price a good indicator?
3. Is it better to buy and sell or hold?

## LON:LOAD Target Price Prediction Modeling Methodology

We consider CRESTCHIC PLC Stock Decision Process with Supervised Machine Learning (ML) where A is the set of discrete actions of LON:LOAD 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(Pearson Correlation)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(Supervised Machine Learning (ML)) X S(n):→ (n+8 weeks) $\stackrel{\to }{S}=\left({s}_{1},{s}_{2},{s}_{3}\right)$

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
Time series to forecast n: 27 Nov 2022 for (n+8 weeks)

According to price forecasts for (n+8 weeks) period: The dominant strategy among neural network is to Sell LON:LOAD 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 CRESTCHIC PLC

1. In accordance with paragraph 4.1.3(a), principal is the fair value of the financial asset at initial recognition. However that principal amount may change over the life of the financial asset (for example, if there are repayments of principal).
2. The definition of a derivative in this Standard includes contracts that are settled gross by delivery of the underlying item (eg a forward contract to purchase a fixed rate debt instrument). An entity may have a contract to buy or sell a non-financial item that can be settled net in cash or another financial instrument or by exchanging financial instruments (eg a contract to buy or sell a commodity at a fixed price at a future date). Such a contract is within the scope of this Standard unless it was entered into and continues to be held for the purpose of delivery of a non-financial item in accordance with the entity's expected purchase, sale or usage requirements. However, this Standard applies to such contracts for an entity's expected purchase, sale or usage requirements if the entity makes a designation in accordance with paragraph 2.5 (see paragraphs 2.4–2.7).
3. If there are changes in circumstances that affect hedge effectiveness, an entity may have to change the method for assessing whether a hedging relationship meets the hedge effectiveness requirements in order to ensure that the relevant characteristics of the hedging relationship, including the sources of hedge ineffectiveness, are still captured.
4. The fact that a derivative is in or out of the money when it is designated as a hedging instrument does not in itself mean that a qualitative assessment is inappropriate. It depends on the circumstances whether hedge ineffectiveness arising from that fact could have a magnitude that a qualitative assessment would not adequately capture.

*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

CRESTCHIC PLC assigned short-term B2 & long-term B2 forecasted stock rating. We evaluate the prediction models Supervised Machine Learning (ML) with Pearson Correlation1,2,3,4 and conclude that the LON:LOAD stock is predictable in the short/long term. According to price forecasts for (n+8 weeks) period: The dominant strategy among neural network is to Sell LON:LOAD stock.

### Financial State Forecast for LON:LOAD CRESTCHIC PLC Stock Options & Futures

Rating Short-Term Long-Term Senior
Outlook*B2B2
Operational Risk 4831
Market Risk4836
Technical Analysis4376
Fundamental Analysis4130
Risk Unsystematic8983

### Prediction Confidence Score

Trust metric by Neural Network: 93 out of 100 with 686 signals.

## References

1. M. Sobel. The variance of discounted Markov decision processes. Applied Probability, pages 794–802, 1982
2. Robins J, Rotnitzky A. 1995. Semiparametric efficiency in multivariate regression models with missing data. J. Am. Stat. Assoc. 90:122–29
3. Bertsimas D, King A, Mazumder R. 2016. Best subset selection via a modern optimization lens. Ann. Stat. 44:813–52
4. Bai J. 2003. Inferential theory for factor models of large dimensions. Econometrica 71:135–71
5. J. Z. Leibo, V. Zambaldi, M. Lanctot, J. Marecki, and T. Graepel. Multi-agent Reinforcement Learning in Sequential Social Dilemmas. In Proceedings of the 16th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2017), Sao Paulo, Brazil, 2017
6. Zou H, Hastie T. 2005. Regularization and variable selection via the elastic net. J. R. Stat. Soc. B 67:301–20
7. Andrews, D. W. K. (1993), "Tests for parameter instability and structural change with unknown change point," Econometrica, 61, 821–856.