Outlook: Advent Technologies Holdings Inc. Class A Common Stock is assigned short-term Ba3 & long-term Ba3 estimated rating.
AUC Score : What is AUC Score?
Short-Term Revised1 :
Time series to forecast n: for Weeks2
Methodology : Statistical Inference (ML)
Hypothesis Testing : Logistic Regression
Surveillance : Major exchange and OTC

1The accuracy of the model is being monitored on a regular basis.(15-minute period)

2Time series is updated based on short-term trends.

## Abstract

Advent Technologies Holdings Inc. Class A Common Stock prediction model is evaluated with Statistical Inference (ML) and Logistic Regression1,2,3,4 and it is concluded that the ADN stock is predictable in the short/long term. Statistical inference is a process of drawing conclusions about a population based on data from a sample of that population. In machine learning (ML), statistical inference is used to make predictions about new data based on data that has already been seen. According to price forecasts for 6 Month period, the dominant strategy among neural network is: Buy

## Key Points

1. Market Signals
2. What are buy sell or hold recommendations?
3. How useful are statistical predictions?

## ADN Target Price Prediction Modeling Methodology

We consider Advent Technologies Holdings Inc. Class A Common Stock Decision Process with Statistical Inference (ML) where A is the set of discrete actions of ADN 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(Logistic 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(Statistical Inference (ML)) X S(n):→ 6 Month $\begin{array}{l}\int {e}^{x}\mathrm{rx}\end{array}$

n:Time series to forecast

j:Nash equilibria (Neural Network)

k:Dominated move

a:Best response for target price

### Statistical Inference (ML)

Statistical inference is a process of drawing conclusions about a population based on data from a sample of that population. In machine learning (ML), statistical inference is used to make predictions about new data based on data that has already been seen.

### Logistic Regression

In statistics, logistic regression is a type of regression analysis used when the dependent variable is categorical. Logistic regression is a probability model that predicts the probability of an event occurring based on a set of independent variables. In logistic regression, the dependent variable is represented as a binary variable, such as "yes" or "no," "true" or "false," or "sick" or "healthy." The independent variables can be continuous or categorical variables.

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: 6 Month

According to price forecasts, the dominant strategy among neural network is: Buy

Strategic Interaction Table Legend:

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%

### Financial Data Adjustments for Statistical Inference (ML) based ADN Stock Prediction Model

1. The expected credit losses on a loan commitment shall be discounted using the effective interest rate, or an approximation thereof, that will be applied when recognising the financial asset resulting from the loan commitment. This is because for the purpose of applying the impairment requirements, a financial asset that is recognised following a draw down on a loan commitment shall be treated as a continuation of that commitment instead of as a new financial instrument. The expected credit losses on the financial asset shall therefore be measured considering the initial credit risk of the loan commitment from the date that the entity became a party to the irrevocable commitment.
3. For floating-rate financial assets and floating-rate financial liabilities, periodic re-estimation of cash flows to reflect the movements in the market rates of interest alters the effective interest rate. If a floating-rate financial asset or a floating-rate financial liability is recognised initially at an amount equal to the principal receivable or payable on maturity, re-estimating the future interest payments normally has no significant effect on the carrying amount of the asset or the liability.
4. Sales that occur for other reasons, such as sales made to manage credit concentration risk (without an increase in the assets' credit risk), may also be consistent with a business model whose objective is to hold financial assets in order to collect contractual cash flows. In particular, such sales may be consistent with a business model whose objective is to hold financial assets in order to collect contractual cash flows if those sales are infrequent (even if significant in value) or insignificant in value both individually and in aggregate (even if frequent). If more than an infrequent number of such sales are made out of a portfolio and those sales are more than insignificant in value (either individually or in aggregate), the entity needs to assess whether and how such sales are consistent with an objective of collecting contractual cash flows. Whether a third party imposes the requirement to sell the financial assets, or that activity is at the entity's discretion, is not relevant to this assessment. An increase in the frequency or value of sales in a particular period is not necessarily inconsistent with an objective to hold financial assets in order to collect contractual cash flows, if an entity can explain the reasons for those sales and demonstrate why those sales do not reflect a change in the entity's business model. In addition, sales may be consistent with the objective of holding financial assets in order to collect contractual cash flows if the sales are made close to the maturity of the financial assets and the proceeds from the sales approximate the collection of the remaining contractual cash flows.

*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.

### ADN Advent Technologies Holdings Inc. Class A Common Stock Financial Analysis*

Rating Short-Term Long-Term Senior
Outlook*Ba3Ba3
Income StatementBaa2Baa2
Balance SheetBaa2C
Leverage RatiosBaa2Baa2
Cash FlowCBaa2
Rates of Return and ProfitabilityB1C

*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?

## Conclusions

Advent Technologies Holdings Inc. Class A Common Stock is assigned short-term Ba3 & long-term Ba3 estimated rating. Advent Technologies Holdings Inc. Class A Common Stock prediction model is evaluated with Statistical Inference (ML) and Logistic Regression1,2,3,4 and it is concluded that the ADN stock is predictable in the short/long term. According to price forecasts for 6 Month period, the dominant strategy among neural network is: Buy

### Prediction Confidence Score

Trust metric by Neural Network: 83 out of 100 with 723 signals.

## References

1. Vapnik V. 2013. The Nature of Statistical Learning Theory. Berlin: Springer
2. 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
3. C. Szepesvári. Algorithms for Reinforcement Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers, 2010
4. Jorgenson, D.W., Weitzman, M.L., ZXhang, Y.X., Haxo, Y.M. and Mat, Y.X., 2023. S&P 500: Is the Bull Market Ready to Run Out of Steam?. AC Investment Research Journal, 220(44).
5. Zeileis A, Hothorn T, Hornik K. 2008. Model-based recursive partitioning. J. Comput. Graph. Stat. 17:492–514 Zhou Z, Athey S, Wager S. 2018. Offline multi-action policy learning: generalization and optimization. arXiv:1810.04778 [stat.ML]
6. D. Bertsekas. Min common/max crossing duality: A geometric view of conjugacy in convex optimization. Lab. for Information and Decision Systems, MIT, Tech. Rep. Report LIDS-P-2796, 2009
7. Candès EJ, Recht B. 2009. Exact matrix completion via convex optimization. Found. Comput. Math. 9:717