CSX Research Report

## Summary

Predictions on stock market prices are a great challenge due to the fact that it is an immensely complex, chaotic and dynamic environment. There are many studies from various areas aiming to take on that challenge and Machine Learning approaches have been the focus of many of them. There are many examples of Machine Learning algorithms been able to reach satisfactory results when doing that type of prediction. This article studies the usage of LSTM networks on that scenario, to predict future trends of stock prices based on the price history, alongside with technical analysis indicators. We evaluate CSX prediction models with Modular Neural Network (News Feed Sentiment Analysis) and Ridge Regression1,2,3,4 and conclude that the CSX stock is predictable in the short/long term. According to price forecasts for (n+3 month) period: The dominant strategy among neural network is to Hold CSX stock.

## Key Points

1. Should I buy stocks now or wait amid such uncertainty?
2. Can we predict stock market using machine learning?
3. What are the most successful trading algorithms?

## CSX Target Price Prediction Modeling Methodology

We consider CSX Stock Decision Process with Modular Neural Network (News Feed Sentiment Analysis) where A is the set of discrete actions of CSX 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(Ridge 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 (News Feed Sentiment Analysis)) X S(n):→ (n+3 month) $∑ i = 1 n s i$

n:Time series to forecast

p:Price signals of CSX 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?

## CSX Stock Forecast (Buy or Sell) for (n+3 month)

Sample Set: Neural Network
Stock/Index: CSX CSX
Time series to forecast n: 20 Nov 2022 for (n+3 month)

According to price forecasts for (n+3 month) period: The dominant strategy among neural network is to Hold CSX 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%

## Adjusted IFRS* Prediction Methods for CSX

1. For a discontinued hedging relationship, when the interest rate benchmark on which the hedged future cash flows had been based is changed as required by interest rate benchmark reform, for the purpose of applying paragraph 6.5.12 in order to determine whether the hedged future cash flows are expected to occur, the amount accumulated in the cash flow hedge reserve for that hedging relationship shall be deemed to be based on the alternative benchmark rate on which the hedged future cash flows will be based.
2. An entity's risk management is the main source of information to perform the assessment of whether a hedging relationship meets the hedge effectiveness requirements. This means that the management information (or analysis) used for decision-making purposes can be used as a basis for assessing whether a hedging relationship meets the hedge effectiveness requirements.
3. If subsequently an entity reasonably expects that the alternative benchmark rate will not be separately identifiable within 24 months from the date the entity designated it as a non-contractually specified risk component for the first time, the entity shall cease applying the requirement in paragraph 6.9.11 to that alternative benchmark rate and discontinue hedge accounting prospectively from the date of that reassessment for all hedging relationships in which the alternative benchmark rate was designated as a noncontractually specified risk component.
4. Paragraphs 6.9.7–6.9.13 provide exceptions to the requirements specified in those paragraphs only. An entity shall apply all other hedge accounting requirements in this Standard, including the qualifying criteria in paragraph 6.4.1, to hedging relationships that were directly affected by interest rate benchmark reform.

*International Financial Reporting Standards (IFRS) are a set of accounting rules for the financial statements of public companies that are intended to make them consistent, transparent, and easily comparable around the world.

## Conclusions

CSX assigned short-term Ba1 & long-term Baa2 forecasted stock rating. We evaluate the prediction models Modular Neural Network (News Feed Sentiment Analysis) with Ridge Regression1,2,3,4 and conclude that the CSX stock is predictable in the short/long term. According to price forecasts for (n+3 month) period: The dominant strategy among neural network is to Hold CSX stock.

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

Rating Short-Term Long-Term Senior
Outlook*Ba1Baa2
Operational Risk 7553
Market Risk5474
Technical Analysis8583
Fundamental Analysis8974
Risk Unsystematic5488

### Prediction Confidence Score

Trust metric by Neural Network: 89 out of 100 with 683 signals.

## References

1. S. Bhatnagar, R. Sutton, M. Ghavamzadeh, and M. Lee. Natural actor-critic algorithms. Automatica, 45(11): 2471–2482, 2009
2. Athey S. 2019. The impact of machine learning on economics. In The Economics of Artificial Intelligence: An Agenda, ed. AK Agrawal, J Gans, A Goldfarb. Chicago: Univ. Chicago Press. In press
3. Kallus N. 2017. Balanced policy evaluation and learning. arXiv:1705.07384 [stat.ML]
4. Jacobs B, Donkers B, Fok D. 2014. Product Recommendations Based on Latent Purchase Motivations. Rotterdam, Neth.: ERIM
5. Scott SL. 2010. A modern Bayesian look at the multi-armed bandit. Appl. Stoch. Models Bus. Ind. 26:639–58
6. Athey S. 2017. Beyond prediction: using big data for policy problems. Science 355:483–85
7. Mnih A, Teh YW. 2012. A fast and simple algorithm for training neural probabilistic language models. In Proceedings of the 29th International Conference on Machine Learning, pp. 419–26. La Jolla, CA: Int. Mach. Learn. Soc.
Frequently Asked QuestionsQ: What is the prediction methodology for CSX stock?
A: CSX stock prediction methodology: We evaluate the prediction models Modular Neural Network (News Feed Sentiment Analysis) and Ridge Regression
Q: Is CSX stock a buy or sell?
A: The dominant strategy among neural network is to Hold CSX Stock.
Q: Is CSX stock a good investment?
A: The consensus rating for CSX is Hold and assigned short-term Ba1 & long-term Baa2 forecasted stock rating.
Q: What is the consensus rating of CSX stock?
A: The consensus rating for CSX is Hold.
Q: What is the prediction period for CSX stock?
A: The prediction period for CSX is (n+3 month)