## Summary

Three networks are compared for low false alarm stock trend predictions. Short-term trends, particularly attractive for neural network analysis, can be used profitably in scenarios such as option trading, but only with significant risk. Therefore, we focus on limiting false alarms, which improves the risk/reward ratio by preventing losses. To predict stock trends, we exploit time delay, recurrent, and probabilistic neural networks (TDNN, RNN, and PNN, respectively), utilizing conjugate gradient and multistream extended Kalman filter training for TDNN and RNN.** We evaluate Old Dominion prediction models with Multi-Instance Learning (ML) and Lasso Regression ^{1,2,3,4} and conclude that the ODFL stock is predictable in the short/long term. **

**According to price forecasts for (n+1 year) period: The dominant strategy among neural network is to Hold ODFL stock.**

## Key Points

- Stock Forecast Based On a Predictive Algorithm
- Market Signals
- Trading Interaction

## ODFL Target Price Prediction Modeling Methodology

We consider Old Dominion Stock Decision Process with Multi-Instance Learning (ML) where A is the set of discrete actions of ODFL 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 Î³ ∈ [0, 1] is a move factor for expectation.^{1,2,3,4}

F(Lasso Regression)

^{5,6,7}= $\begin{array}{cccc}{p}_{\mathrm{a}1}& {p}_{\mathrm{a}2}& \dots & {p}_{1n}\\ & \vdots \\ {p}_{j1}& {p}_{j2}& \dots & {p}_{jn}\\ & \vdots \\ {p}_{k1}& {p}_{k2}& \dots & {p}_{kn}\\ & \vdots \\ {p}_{n1}& {p}_{n2}& \dots & {p}_{nn}\end{array}$ X R(Multi-Instance Learning (ML)) X S(n):→ (n+1 year) $\begin{array}{l}\int {r}^{s}\mathrm{rs}\end{array}$

n:Time series to forecast

p:Price signals of ODFL 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?

## ODFL Stock Forecast (Buy or Sell) for (n+1 year)

**Sample Set:**Neural Network

**Stock/Index:**ODFL Old Dominion

**Time series to forecast n: 18 Nov 2022**for (n+1 year)

**According to price forecasts for (n+1 year) period: The dominant strategy among neural network is to Hold ODFL 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 Old Dominion

- IFRS 16, issued in January 2016, amended paragraphs 2.1, 5.5.15, B4.3.8, B5.5.34 and B5.5.46. An entity shall apply those amendments when it applies IFRS 16.
- Paragraph 6.3.4 permits an entity to designate as hedged items aggregated exposures that are a combination of an exposure and a derivative. When designating such a hedged item, an entity assesses whether the aggregated exposure combines an exposure with a derivative so that it creates a different aggregated exposure that is managed as one exposure for a particular risk (or risks). In that case, the entity may designate the hedged item on the basis of the aggregated exposure
- The fair value of a financial instrument at initial recognition is normally the transaction price (ie the fair value of the consideration given or received, see also paragraph B5.1.2A and IFRS 13). However, if part of the consideration given or received is for something other than the financial instrument, an entity shall measure the fair value of the financial instrument. For example, the fair value of a long-term loan or receivable that carries no interest can be measured as the present value of all future cash receipts discounted using the prevailing market rate(s) of interest for a similar instrument (similar as to currency, term, type of interest rate and other factors) with a similar credit rating. Any additional amount lent is an expense or a reduction of income unless it qualifies for recognition as some other type of asset.
- In the reporting period that includes the date of initial application of these amendments, an entity is not required to present the quantitative information required by paragraph 28(f) of IAS 8.

*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

Old Dominion assigned short-term B2 & long-term Ba3 forecasted stock rating.** We evaluate the prediction models Multi-Instance Learning (ML) with Lasso Regression ^{1,2,3,4} and conclude that the ODFL stock is predictable in the short/long term.**

**According to price forecasts for (n+1 year) period: The dominant strategy among neural network is to Hold ODFL stock.**

### Financial State Forecast for ODFL Old Dominion Stock Options & Futures

Rating | Short-Term | Long-Term Senior |
---|---|---|

Outlook* | B2 | Ba3 |

Operational Risk | 82 | 83 |

Market Risk | 38 | 77 |

Technical Analysis | 68 | 56 |

Fundamental Analysis | 51 | 46 |

Risk Unsystematic | 42 | 57 |

### Prediction Confidence Score

## References

- J. Peters, S. Vijayakumar, and S. Schaal. Natural actor-critic. In Proceedings of the Sixteenth European Conference on Machine Learning, pages 280–291, 2005.
- Bottou L. 1998. Online learning and stochastic approximations. In On-Line Learning in Neural Networks, ed. D Saad, pp. 9–42. New York: ACM
- Clements, M. P. D. F. Hendry (1995), "Forecasting in cointegrated systems," Journal of Applied Econometrics, 10, 127–146.
- Chernozhukov V, Chetverikov D, Demirer M, Duflo E, Hansen C, et al. 2018a. Double/debiased machine learning for treatment and structural parameters. Econom. J. 21:C1–68
- Scholkopf B, Smola AJ. 2001. Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. Cambridge, MA: MIT Press
- Swaminathan A, Joachims T. 2015. Batch learning from logged bandit feedback through counterfactual risk minimization. J. Mach. Learn. Res. 16:1731–55
- Sutton RS, Barto AG. 1998. Reinforcement Learning: An Introduction. Cambridge, MA: MIT Press

## Frequently Asked Questions

Q: What is the prediction methodology for ODFL stock?A: ODFL stock prediction methodology: We evaluate the prediction models Multi-Instance Learning (ML) and Lasso Regression

Q: Is ODFL stock a buy or sell?

A: The dominant strategy among neural network is to Hold ODFL Stock.

Q: Is Old Dominion stock a good investment?

A: The consensus rating for Old Dominion is Hold and assigned short-term B2 & long-term Ba3 forecasted stock rating.

Q: What is the consensus rating of ODFL stock?

A: The consensus rating for ODFL is Hold.

Q: What is the prediction period for ODFL stock?

A: The prediction period for ODFL is (n+1 year)