Outlook: KeyCorp Depositary Shares Each Representing a 1/40th Ownership Interest in a Share of Fixed-to-Floating Rate Perpetual Non-Cumulative Preferred Stock Series E is assigned short-term Ba1 & long-term Ba1 estimated rating.
Dominant Strategy : Sell
Time series to forecast n: 31 Mar 2023 for (n+1 year)
Methodology : Modular Neural Network (Market Volatility Analysis)

## Abstract

KeyCorp Depositary Shares Each Representing a 1/40th Ownership Interest in a Share of Fixed-to-Floating Rate Perpetual Non-Cumulative Preferred Stock Series E prediction model is evaluated with Modular Neural Network (Market Volatility Analysis) and Polynomial Regression1,2,3,4 and it is concluded that the KEY^I stock is predictable in the short/long term. According to price forecasts for (n+1 year) period, the dominant strategy among neural network is: Sell

## Key Points

1. How useful are statistical predictions?
2. What statistical methods are used to analyze data?
3. Trust metric by Neural Network

## KEY^I Target Price Prediction Modeling Methodology

We consider KeyCorp Depositary Shares Each Representing a 1/40th Ownership Interest in a Share of Fixed-to-Floating Rate Perpetual Non-Cumulative Preferred Stock Series E Decision Process with Modular Neural Network (Market Volatility Analysis) where A is the set of discrete actions of KEY^I 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 (Market Volatility Analysis)) X S(n):→ (n+1 year) $\stackrel{\to }{R}=\left({r}_{1},{r}_{2},{r}_{3}\right)$

n:Time series to forecast

p:Price signals of KEY^I 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^I Stock Forecast (Buy or Sell) for (n+1 year)

Sample Set: Neural Network
Stock/Index: KEY^I KeyCorp Depositary Shares Each Representing a 1/40th Ownership Interest in a Share of Fixed-to-Floating Rate Perpetual Non-Cumulative Preferred Stock Series E
Time series to forecast n: 31 Mar 2023 for (n+1 year)

According to price forecasts for (n+1 year) 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-to-Floating Rate Perpetual Non-Cumulative Preferred Stock Series E

1. An entity's business model refers to how an entity manages its financial assets in order to generate cash flows. That is, the entity's business model determines whether cash flows will result from collecting contractual cash flows, selling financial assets or both. Consequently, this assessment is not performed on the basis of scenarios that the entity does not reasonably expect to occur, such as so-called 'worst case' or 'stress case' scenarios. For example, if an entity expects that it will sell a particular portfolio of financial assets only in a stress case scenario, that scenario would not affect the entity's assessment of the business model for those assets if the entity reasonably expects that such a scenario will not occur. If cash flows are realised in a way that is different from the entity's expectations at the date that the entity assessed the business model (for example, if the entity sells more or fewer financial assets than it expected when it classified the assets), that does not give rise to a prior period error in the entity's financial statements (see IAS 8 Accounting Policies, Changes in Accounting Estimates and Errors) nor does it change the classification of the remaining financial assets held in that business model (ie those assets that the entity recognised in prior periods and still holds) as long as the entity considered all relevant information that was available at the time that it made the business model assessment.
2. When an entity designates a financial liability as at fair value through profit or loss, it must determine whether presenting in other comprehensive income the effects of changes in the liability's credit risk would create or enlarge an accounting mismatch in profit or loss. An accounting mismatch would be created or enlarged if presenting the effects of changes in the liability's credit risk in other comprehensive income would result in a greater mismatch in profit or loss than if those amounts were presented in profit or loss
3. Lifetime expected credit losses are generally expected to be recognised before a financial instrument becomes past due. Typically, credit risk increases significantly before a financial instrument becomes past due or other lagging borrower-specific factors (for example, a modification or restructuring) are observed. Consequently when reasonable and supportable information that is more forward-looking than past due information is available without undue cost or effort, it must be used to assess changes in credit risk.
4. At the date of initial application, an entity shall use reasonable and supportable information that is available without undue cost or effort to determine the credit risk at the date that a financial instrument was initially recognised (or for loan commitments and financial guarantee contracts at the date that the entity became a party to the irrevocable commitment in accordance with paragraph 5.5.6) and compare that to the credit risk at the date of initial application of this Standard.

*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-to-Floating Rate Perpetual Non-Cumulative Preferred Stock Series E 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-to-Floating Rate Perpetual Non-Cumulative Preferred Stock Series E prediction model is evaluated with Modular Neural Network (Market Volatility Analysis) and Polynomial Regression1,2,3,4 and it is concluded that the KEY^I stock is predictable in the short/long term. According to price forecasts for (n+1 year) period, the dominant strategy among neural network is: Sell

### KEY^I KeyCorp Depositary Shares Each Representing a 1/40th Ownership Interest in a Share of Fixed-to-Floating Rate Perpetual Non-Cumulative Preferred Stock Series E Financial Analysis*

Rating Short-Term Long-Term Senior
Outlook*Ba1Ba1
Income StatementB3Ba2
Balance SheetCaa2Baa2
Leverage RatiosBaa2C
Cash FlowBa2C
Rates of Return and ProfitabilityCBaa2

*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: 89 out of 100 with 452 signals.

## References

1. C. Wu and Y. Lin. Minimizing risk models in Markov decision processes with policies depending on target values. Journal of Mathematical Analysis and Applications, 231(1):47–67, 1999
2. R. Rockafellar and S. Uryasev. Conditional value-at-risk for general loss distributions. Journal of Banking and Finance, 26(7):1443 – 1471, 2002
3. Bastani H, Bayati M. 2015. Online decision-making with high-dimensional covariates. Work. Pap., Univ. Penn./ Stanford Grad. School Bus., Philadelphia/Stanford, CA
4. Abadie A, Diamond A, Hainmueller J. 2010. Synthetic control methods for comparative case studies: estimat- ing the effect of California's tobacco control program. J. Am. Stat. Assoc. 105:493–505
5. J. Baxter and P. Bartlett. Infinite-horizon policy-gradient estimation. Journal of Artificial Intelligence Re- search, 15:319–350, 2001.
6. Bessler, D. A. T. Covey (1991), "Cointegration: Some results on U.S. cattle prices," Journal of Futures Markets, 11, 461–474.
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]
Frequently Asked QuestionsQ: What is the prediction methodology for KEY^I stock?
A: KEY^I stock prediction methodology: We evaluate the prediction models Modular Neural Network (Market Volatility Analysis) and Polynomial Regression
Q: Is KEY^I stock a buy or sell?
A: The dominant strategy among neural network is to Sell KEY^I Stock.
Q: Is KeyCorp Depositary Shares Each Representing a 1/40th Ownership Interest in a Share of Fixed-to-Floating Rate Perpetual Non-Cumulative Preferred Stock Series E stock a good investment?
A: The consensus rating for KeyCorp Depositary Shares Each Representing a 1/40th Ownership Interest in a Share of Fixed-to-Floating Rate Perpetual Non-Cumulative Preferred Stock Series E is Sell and is assigned short-term Ba1 & long-term Ba1 estimated rating.
Q: What is the consensus rating of KEY^I stock?
A: The consensus rating for KEY^I is Sell.
Q: What is the prediction period for KEY^I stock?
A: The prediction period for KEY^I is (n+1 year)