Outlook: KeyCorp Depositary Shares each representing a 1/40th ownership interest in a share of Fixed Rate Perpetual Non-Cumulative Preferred Stock Series H is assigned short-term Ba1 & long-term Ba1 estimated rating.
Dominant Strategy : Sell
Time series to forecast n: 26 Mar 2023 for (n+16 weeks)
Methodology : Modular Neural Network (DNN Layer)

## Abstract

KeyCorp Depositary Shares each representing a 1/40th ownership interest in a share of Fixed Rate Perpetual Non-Cumulative Preferred Stock Series H prediction model is evaluated with Modular Neural Network (DNN Layer) and Polynomial Regression1,2,3,4 and it is concluded that the KEY^L 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. Decision Making
2. Can we predict stock market using machine learning?
3. What are main components of Markov decision process?

## KEY^L Target Price Prediction Modeling Methodology

We consider KeyCorp Depositary Shares each representing a 1/40th ownership interest in a share of Fixed Rate Perpetual Non-Cumulative Preferred Stock Series H Decision Process with Modular Neural Network (DNN Layer) where A is the set of discrete actions of KEY^L 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(Polynomial 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 (DNN Layer)) X S(n):→ (n+16 weeks) $\begin{array}{l}\int {e}^{x}\mathrm{rx}\end{array}$

n:Time series to forecast

p:Price signals of KEY^L stock

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?

## KEY^L Stock Forecast (Buy or Sell) for (n+16 weeks)

Sample Set: Neural Network
Stock/Index: KEY^L KeyCorp Depositary Shares each representing a 1/40th ownership interest in a share of Fixed Rate Perpetual Non-Cumulative Preferred Stock Series H
Time series to forecast n: 26 Mar 2023 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%

## IFRS Reconciliation Adjustments for KeyCorp Depositary Shares each representing a 1/40th ownership interest in a share of Fixed Rate Perpetual Non-Cumulative Preferred Stock Series H

1. If a financial instrument is designated in accordance with paragraph 6.7.1 as measured at fair value through profit or loss after its initial recognition, or was previously not recognised, the difference at the time of designation between the carrying amount, if any, and the fair value shall immediately be recognised in profit or loss. For financial assets measured at fair value through other comprehensive income in accordance with paragraph 4.1.2A, the cumulative gain or loss previously recognised in other comprehensive income shall immediately be reclassified from equity to profit or loss as a reclassification adjustment.
2. However, in some cases, the time value of money element may be modified (ie imperfect). That would be the case, for example, if a financial asset's interest rate is periodically reset but the frequency of that reset does not match the tenor of the interest rate (for example, the interest rate resets every month to a one-year rate) or if a financial asset's interest rate is periodically reset to an average of particular short- and long-term interest rates. In such cases, an entity must assess the modification to determine whether the contractual cash flows represent solely payments of principal and interest on the principal amount outstanding. In some circumstances, the entity may be able to make that determination by performing a qualitative assessment of the time value of money element whereas, in other circumstances, it may be necessary to perform a quantitative assessment.
3. Measurement of a financial asset or financial liability and classification of recognised changes in its value are determined by the item's classification and whether the item is part of a designated hedging relationship. Those requirements can create a measurement or recognition inconsistency (sometimes referred to as an 'accounting mismatch') when, for example, in the absence of designation as at fair value through profit or loss, a financial asset would be classified as subsequently measured at fair value through profit or loss and a liability the entity considers related would be subsequently measured at amortised cost (with changes in fair value not recognised). In such circumstances, an entity may conclude that its financial statements would provide more relevant information if both the asset and the liability were measured as at fair value through profit or loss.
4. At the date of initial application, an entity shall determine whether the treatment in paragraph 5.7.7 would create or enlarge an accounting mismatch in profit or loss on the basis of the facts and circumstances that exist at the date of initial application. This Standard shall be applied retrospectively on the basis of that determination.

*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

KeyCorp Depositary Shares each representing a 1/40th ownership interest in a share of Fixed Rate Perpetual Non-Cumulative Preferred Stock Series H is assigned short-term Ba1 & long-term Ba1 estimated rating. KeyCorp Depositary Shares each representing a 1/40th ownership interest in a share of Fixed Rate Perpetual Non-Cumulative Preferred Stock Series H prediction model is evaluated with Modular Neural Network (DNN Layer) and Polynomial Regression1,2,3,4 and it is concluded that the KEY^L 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^L KeyCorp Depositary Shares each representing a 1/40th ownership interest in a share of Fixed Rate Perpetual Non-Cumulative Preferred Stock Series H Financial Analysis*

Rating Short-Term Long-Term Senior
Outlook*Ba1Ba1
Income StatementCB1
Balance SheetCaa2B3
Leverage RatiosCC
Cash FlowBaa2Caa2
Rates of Return and ProfitabilityCB2

*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: 88 out of 100 with 870 signals. ## References

1. Abadir, K. M., K. Hadri E. Tzavalis (1999), "The influence of VAR dimensions on estimator biases," Econometrica, 67, 163–181.
2. 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.
3. J. Spall. Multivariate stochastic approximation using a simultaneous perturbation gradient approximation. IEEE Transactions on Automatic Control, 37(3):332–341, 1992.
4. M. Benaim, J. Hofbauer, and S. Sorin. Stochastic approximations and differential inclusions, Part II: Appli- cations. Mathematics of Operations Research, 31(4):673–695, 2006
5. Doudchenko N, Imbens GW. 2016. Balancing, regression, difference-in-differences and synthetic control methods: a synthesis. NBER Work. Pap. 22791
6. Brailsford, T.J. R.W. Faff (1996), "An evaluation of volatility forecasting techniques," Journal of Banking Finance, 20, 419–438.
7. Wu X, Kumar V, Quinlan JR, Ghosh J, Yang Q, et al. 2008. Top 10 algorithms in data mining. Knowl. Inform. Syst. 14:1–37
Frequently Asked QuestionsQ: What is the prediction methodology for KEY^L stock?
A: KEY^L stock prediction methodology: We evaluate the prediction models Modular Neural Network (DNN Layer) and Polynomial Regression
Q: Is KEY^L stock a buy or sell?
A: The dominant strategy among neural network is to Sell KEY^L Stock.
Q: Is KeyCorp Depositary Shares each representing a 1/40th ownership interest in a share of Fixed Rate Perpetual Non-Cumulative Preferred Stock Series H stock a good investment?
A: The consensus rating for KeyCorp Depositary Shares each representing a 1/40th ownership interest in a share of Fixed Rate Perpetual Non-Cumulative Preferred Stock Series H is Sell and is assigned short-term Ba1 & long-term Ba1 estimated rating.
Q: What is the consensus rating of KEY^L stock?
A: The consensus rating for KEY^L is Sell.
Q: What is the prediction period for KEY^L stock?
A: The prediction period for KEY^L is (n+16 weeks)