Outlook: Scienjoy Holding Corporation Class A Ordinary Shares is assigned short-term B3 & long-term B1 estimated rating.
Daily Trading Strategy :
Dominant Strategy : Buy
Time series to forecast n: for 16 Weeks
Methodology : Transductive Learning (ML)

## Summary

Scienjoy Holding Corporation Class A Ordinary Shares prediction model is evaluated with Transductive Learning (ML) and Wilcoxon Sign-Rank Test1,2,3,4 and it is concluded that the SJ stock is predictable in the short/long term. Transductive learning is a supervised machine learning (ML) method in which the model is trained on both labeled and unlabeled data. The goal of transductive learning is to predict the labels of the unlabeled data. Transductive learning is a hybrid of inductive and semi-supervised learning. Inductive learning algorithms are trained on labeled data only, while semi-supervised learning algorithms are trained on a combination of labeled and unlabeled data. Transductive learning algorithms can achieve better performance than inductive learning algorithms on tasks where there is a small amount of labeled data. This is because transductive learning algorithms can use the unlabeled data to help them learn the relationships between the features and the labels. According to price forecasts for 16 Weeks period, the dominant strategy among neural network is: Buy

## Key Points

1. What is prediction in deep learning?
2. How do you decide buy or sell a stock?
3. What is prediction model?

## SJ Target Price Prediction Modeling Methodology

We consider Scienjoy Holding Corporation Class A Ordinary Shares Decision Process with Transductive Learning (ML) where A is the set of discrete actions of SJ 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(Wilcoxon Sign-Rank Test)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(Transductive Learning (ML)) X S(n):→ 16 Weeks $\begin{array}{l}\int {e}^{x}\mathrm{rx}\end{array}$

n:Time series to forecast

p:Price signals of SJ stock

j:Nash equilibria (Neural Network)

k:Dominated move

a:Best response for target price

### Transductive Learning (ML)

Transductive learning is a supervised machine learning (ML) method in which the model is trained on both labeled and unlabeled data. The goal of transductive learning is to predict the labels of the unlabeled data. Transductive learning is a hybrid of inductive and semi-supervised learning. Inductive learning algorithms are trained on labeled data only, while semi-supervised learning algorithms are trained on a combination of labeled and unlabeled data. Transductive learning algorithms can achieve better performance than inductive learning algorithms on tasks where there is a small amount of labeled data. This is because transductive learning algorithms can use the unlabeled data to help them learn the relationships between the features and the labels.

### Wilcoxon Sign-Rank Test

The Wilcoxon rank-sum test, also known as the Mann-Whitney U test, is a non-parametric test that is used to compare the medians of two independent samples. It is a rank-based test, which means that it does not assume that the data is normally distributed. The Wilcoxon rank-sum test is calculated by first ranking the data from both samples, and then finding the sum of the ranks for one of the samples. The Wilcoxon rank-sum test statistic is then calculated by subtracting the sum of the ranks for one sample from the sum of the ranks for the other sample. The p-value for the Wilcoxon rank-sum test is calculated using a table of critical values. The p-value is the probability of obtaining a test statistic at least as extreme as the one observed, assuming that the null hypothesis is true.

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?

## SJ Stock Forecast (Buy or Sell) for 16 Weeks

Sample Set: Neural Network
Stock/Index: SJ Scienjoy Holding Corporation Class A Ordinary Shares
Time series to forecast n: 16 Weeks

According to price forecasts for 16 Weeks period, the dominant strategy among neural network is: Buy

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 Scienjoy Holding Corporation Class A Ordinary Shares

1. The underlying pool must contain one or more instruments that have contractual cash flows that are solely payments of principal and interest on the principal amount outstanding
2. Amounts presented in other comprehensive income shall not be subsequently transferred to profit or loss. However, the entity may transfer the cumulative gain or loss within equity.
3. Lifetime expected credit losses are not recognised on a financial instrument simply because it was considered to have low credit risk in the previous reporting period and is not considered to have low credit risk at the reporting date. In such a case, an entity shall determine whether there has been a significant increase in credit risk since initial recognition and thus whether lifetime expected credit losses are required to be recognised in accordance with paragraph 5.5.3.
4. A hedge of a firm commitment (for example, a hedge of the change in fuel price relating to an unrecognised contractual commitment by an electric utility to purchase fuel at a fixed price) is a hedge of an exposure to a change in fair value. Accordingly, such a hedge is a fair value hedge. However, in accordance with paragraph 6.5.4, a hedge of the foreign currency risk of a firm commitment could alternatively be accounted for as a cash flow hedge.

*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

Scienjoy Holding Corporation Class A Ordinary Shares is assigned short-term B3 & long-term B1 estimated rating. Scienjoy Holding Corporation Class A Ordinary Shares prediction model is evaluated with Transductive Learning (ML) and Wilcoxon Sign-Rank Test1,2,3,4 and it is concluded that the SJ stock is predictable in the short/long term. According to price forecasts for 16 Weeks period, the dominant strategy among neural network is: Buy

### SJ Scienjoy Holding Corporation Class A Ordinary Shares Financial Analysis*

Rating Short-Term Long-Term Senior
Outlook*B3B1
Income StatementBaa2Baa2
Balance SheetB1C
Leverage RatiosCCaa2
Cash FlowCaa2Baa2
Rates of Return and ProfitabilityCaa2Ba3

*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: 81 out of 100 with 639 signals.

## References

1. C. Szepesvári. Algorithms for Reinforcement Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers, 2010
2. V. Konda and J. Tsitsiklis. Actor-Critic algorithms. In Proceedings of Advances in Neural Information Processing Systems 12, pages 1008–1014, 2000
3. S. J. Russell and A. Zimdars. Q-decomposition for reinforcement learning agents. In Machine Learning, Proceedings of the Twentieth International Conference (ICML 2003), August 21-24, 2003, Washington, DC, USA, pages 656–663, 2003.
4. Matzkin RL. 2007. Nonparametric identification. In Handbook of Econometrics, Vol. 6B, ed. J Heckman, E Learner, pp. 5307–68. Amsterdam: Elsevier
5. Athey S, Tibshirani J, Wager S. 2016b. Generalized random forests. arXiv:1610.01271 [stat.ME]
6. S. Bhatnagar, H. Prasad, and L. Prashanth. Stochastic recursive algorithms for optimization, volume 434. Springer, 2013
7. V. Mnih, A. P. Badia, M. Mirza, A. Graves, T. P. Lillicrap, T. Harley, D. Silver, and K. Kavukcuoglu. Asynchronous methods for deep reinforcement learning. In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016, pages 1928–1937, 2016
Frequently Asked QuestionsQ: What is the prediction methodology for SJ stock?
A: SJ stock prediction methodology: We evaluate the prediction models Transductive Learning (ML) and Wilcoxon Sign-Rank Test
Q: Is SJ stock a buy or sell?
A: The dominant strategy among neural network is to Buy SJ Stock.
Q: Is Scienjoy Holding Corporation Class A Ordinary Shares stock a good investment?
A: The consensus rating for Scienjoy Holding Corporation Class A Ordinary Shares is Buy and is assigned short-term B3 & long-term B1 estimated rating.
Q: What is the consensus rating of SJ stock?
A: The consensus rating for SJ is Buy.
Q: What is the prediction period for SJ stock?
A: The prediction period for SJ is 16 Weeks