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 Royal Bank of Canada prediction models with Modular Neural Network (Financial Sentiment Analysis) and Stepwise Regression1,2,3,4 and conclude that the RY stock is predictable in the short/long term. According to price forecasts for (n+4 weeks) period: The dominant strategy among neural network is to Hold RY stock.

Keywords: RY, Royal Bank of Canada, stock forecast, machine learning based prediction, risk rating, buy-sell behaviour, stock analysis, target price analysis, options and futures.

## Key Points

1. Stock Forecast Based On a Predictive Algorithm
2. Is it better to buy and sell or hold?
3. How accurate is machine learning in stock market? ## RY Target Price Prediction Modeling Methodology

In this paper a Bayesian regularized artificial neural network is proposed as a novel method to forecast financial market behavior. Daily market prices and financial technical indicators are utilized as inputs to predict the one day future closing price of individual stocks. The prediction of stock price movement is generally considered to be a challenging and important task for financial time series analysis. We consider Royal Bank of Canada Stock Decision Process with Stepwise Regression where A is the set of discrete actions of RY 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(Stepwise 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(Modular Neural Network (Financial Sentiment Analysis)) X S(n):→ (n+4 weeks) $∑ i = 1 n r i$

n:Time series to forecast

p:Price signals of RY stock

j:Nash equilibria

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?

## RY Stock Forecast (Buy or Sell) for (n+4 weeks)

Sample Set: Neural Network
Stock/Index: RY Royal Bank of Canada
Time series to forecast n: 14 Nov 2022 for (n+4 weeks)

According to price forecasts for (n+4 weeks) period: The dominant strategy among neural network is to Hold RY 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%

1. If a call option right retained by an entity prevents a transferred asset from being derecognised and the entity measures the transferred asset at fair value, the asset continues to be measured at its fair value. The associated liability is measured at (i) the option exercise price less the time value of the option if the option is in or at the money, or (ii) the fair value of the transferred asset less the time value of the option if the option is out of the money. The adjustment to the measurement of the associated liability ensures that the net carrying amount of the asset and the associated liability is the fair value of the call option right. For example, if the fair value of the underlying asset is CU80, the option exercise price is CU95 and the time value of the option is CU5, the carrying amount of the associated liability is CU75 (CU80 – CU5) and the carrying amount of the transferred asset is CU80 (ie its fair value)
2. Expected credit losses shall be discounted to the reporting date, not to the expected default or some other date, using the effective interest rate determined at initial recognition or an approximation thereof. If a financial instrument has a variable interest rate, expected credit losses shall be discounted using the current effective interest rate determined in accordance with paragraph B5.4.5.
3. If a call option right retained by an entity prevents a transferred asset from being derecognised and the entity measures the transferred asset at fair value, the asset continues to be measured at its fair value. The associated liability is measured at (i) the option exercise price less the time value of the option if the option is in or at the money, or (ii) the fair value of the transferred asset less the time value of the option if the option is out of the money. The adjustment to the measurement of the associated liability ensures that the net carrying amount of the asset and the associated liability is the fair value of the call option right. For example, if the fair value of the underlying asset is CU80, the option exercise price is CU95 and the time value of the option is CU5, the carrying amount of the associated liability is CU75 (CU80 – CU5) and the carrying amount of the transferred asset is CU80 (ie its fair value)
4. Conversely, if changes in the extent of offset indicate that the fluctuation is around a hedge ratio that is different from the hedge ratio that is currently used for that hedging relationship, or that there is a trend leading away from that hedge ratio, hedge ineffectiveness can be reduced by adjusting the hedge ratio, whereas retaining the hedge ratio would increasingly produce hedge ineffectiveness. Hence, in such circumstances, an entity must evaluate whether the hedging relationship reflects an imbalance between the weightings of the hedged item and the hedging instrument that would create hedge ineffectiveness (irrespective of whether recognised or not) that could result in an accounting outcome that would be inconsistent with the purpose of hedge accounting. If the hedge ratio is adjusted, it also affects the measurement and recognition of hedge ineffectiveness because, on rebalancing, the hedge ineffectiveness of the hedging relationship must be determined and recognised immediately before adjusting the hedging relationship in accordance with paragraph B6.5.8.

*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

Royal Bank of Canada assigned short-term B3 & long-term Ba1 forecasted stock rating. We evaluate the prediction models Modular Neural Network (Financial Sentiment Analysis) with Stepwise Regression1,2,3,4 and conclude that the RY stock is predictable in the short/long term. According to price forecasts for (n+4 weeks) period: The dominant strategy among neural network is to Hold RY stock.

### Financial State Forecast for RY Royal Bank of Canada Stock Options & Futures

Rating Short-Term Long-Term Senior
Outlook*B3Ba1
Operational Risk 7175
Market Risk3669
Technical Analysis7267
Fundamental Analysis3275
Risk Unsystematic4474

### Prediction Confidence Score

Trust metric by Neural Network: 83 out of 100 with 810 signals.

## References

1. C. Claus and C. Boutilier. The dynamics of reinforcement learning in cooperative multiagent systems. In Proceedings of the Fifteenth National Conference on Artificial Intelligence and Tenth Innovative Applications of Artificial Intelligence Conference, AAAI 98, IAAI 98, July 26-30, 1998, Madison, Wisconsin, USA., pages 746–752, 1998.
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. T. Shardlow and A. Stuart. A perturbation theory for ergodic Markov chains and application to numerical approximations. SIAM journal on numerical analysis, 37(4):1120–1137, 2000
4. R. Williams. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Ma- chine learning, 8(3-4):229–256, 1992
5. Keane MP. 2013. Panel data discrete choice models of consumer demand. In The Oxford Handbook of Panel Data, ed. BH Baltagi, pp. 54–102. Oxford, UK: Oxford Univ. Press
6. J. N. Foerster, Y. M. Assael, N. de Freitas, and S. Whiteson. Learning to communicate with deep multi-agent reinforcement learning. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5-10, 2016, Barcelona, Spain, pages 2137–2145, 2016.
7. S. Bhatnagar and K. Lakshmanan. An online actor-critic algorithm with function approximation for con- strained Markov decision processes. Journal of Optimization Theory and Applications, 153(3):688–708, 2012.
Frequently Asked QuestionsQ: What is the prediction methodology for RY stock?
A: RY stock prediction methodology: We evaluate the prediction models Modular Neural Network (Financial Sentiment Analysis) and Stepwise Regression
Q: Is RY stock a buy or sell?
A: The dominant strategy among neural network is to Hold RY Stock.
Q: Is Royal Bank of Canada stock a good investment?
A: The consensus rating for Royal Bank of Canada is Hold and assigned short-term B3 & long-term Ba1 forecasted stock rating.
Q: What is the consensus rating of RY stock?
A: The consensus rating for RY is Hold.
Q: What is the prediction period for RY stock?
A: The prediction period for RY is (n+4 weeks)