Nowadays, people show more and more enthusiasm for applying machine learning methods to finance domain. Many scholars and investors are trying to discover the mystery behind the stock market by applying deep learning. This thesis compares four machine learning methods: long short-term memory (LSTM), gated recurrent units (GRU), support vector machine (SVM), and eXtreme gradient boosting (XGBoost) to test which one performs the best in predicting the stock trend. We evaluate Southern Company prediction models with Modular Neural Network (Speculative Sentiment Analysis) and Sign Test1,2,3,4 and conclude that the SO 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 SO stock.

Keywords: SO, Southern Company, stock forecast, machine learning based prediction, risk rating, buy-sell behaviour, stock analysis, target price analysis, options and futures.

## Key Points

1. What are main components of Markov decision process?
2. What are the most successful trading algorithms?
3. Is it better to buy and sell or hold?

## SO Target Price Prediction Modeling Methodology

The aim of this study is to evaluate the effectiveness of using external indicators, such as commodity prices and currency exchange rates, in predicting movements. The performance of each technique is evaluated using different domain specific metrics. A comprehensive evaluation procedure is described, involving the use of trading simulations to assess the practical value of predictive models, and comparison with simple benchmarks that respond to underlying market growth. We consider Southern Company Stock Decision Process with Sign Test where A is the set of discrete actions of SO 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(Sign 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(Modular Neural Network (Speculative Sentiment Analysis)) X S(n):→ (n+4 weeks) $\stackrel{\to }{S}=\left({s}_{1},{s}_{2},{s}_{3}\right)$

n:Time series to forecast

p:Price signals of SO 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?

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

Sample Set: Neural Network
Stock/Index: SO Southern Company
Time series to forecast n: 19 Sep 2022 for (n+4 weeks)

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

## Conclusions

Southern Company assigned short-term B1 & long-term Ba3 forecasted stock rating. We evaluate the prediction models Modular Neural Network (Speculative Sentiment Analysis) with Sign Test1,2,3,4 and conclude that the SO 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 SO stock.

### Financial State Forecast for SO Stock Options & Futures

Rating Short-Term Long-Term Senior
Outlook*B1Ba3
Operational Risk 4578
Market Risk5250
Technical Analysis7544
Fundamental Analysis6075
Risk Unsystematic5881

### Prediction Confidence Score

Trust metric by Neural Network: 73 out of 100 with 583 signals.

## References

1. 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
2. Chernozhukov V, Escanciano JC, Ichimura H, Newey WK. 2016b. Locally robust semiparametric estimation. arXiv:1608.00033 [math.ST]
3. Byron, R. P. O. Ashenfelter (1995), "Predicting the quality of an unborn grange," Economic Record, 71, 40–53.
4. Chernozhukov V, Chetverikov D, Demirer M, Duflo E, Hansen C, et al. 2016a. Double machine learning for treatment and causal parameters. Tech. Rep., Cent. Microdata Methods Pract., Inst. Fiscal Stud., London
5. Clements, M. P. D. F. Hendry (1997), "An empirical study of seasonal unit roots in forecasting," International Journal of Forecasting, 13, 341–355.
6. Tibshirani R. 1996. Regression shrinkage and selection via the lasso. J. R. Stat. Soc. B 58:267–88
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 SO stock?
A: SO stock prediction methodology: We evaluate the prediction models Modular Neural Network (Speculative Sentiment Analysis) and Sign Test
Q: Is SO stock a buy or sell?
A: The dominant strategy among neural network is to Hold SO Stock.
Q: Is Southern Company stock a good investment?
A: The consensus rating for Southern Company is Hold and assigned short-term B1 & long-term Ba3 forecasted stock rating.
Q: What is the consensus rating of SO stock?
A: The consensus rating for SO is Hold.
Q: What is the prediction period for SO stock?
A: The prediction period for SO is (n+4 weeks)