HXT:TSX Stock: A Cautionary Tale

Outlook: Horizons S&P/TSX 60 Index ETF is assigned short-term Ba1 & long-term B2 estimated rating.
AUC Score : What is AUC Score?
Short-Term Revised¹ :
Dominant Strategy : Sell
Time series to forecast n: for Weeks²
Methodology : Modular Neural Network (Market News Sentiment Analysis)
Hypothesis Testing : Wilcoxon Sign-Rank Test
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.

Summary

Horizons S&P/TSX 60 Index ETF prediction model is evaluated with Modular Neural Network (Market News Sentiment Analysis) and Wilcoxon Sign-Rank Test^1,2,3,4 and it is concluded that the HXT:TSX stock is predictable in the short/long term. A modular neural network (MNN) is a type of artificial neural network that can be used for news feed sentiment analysis. MNNs are made up of multiple smaller neural networks, called modules. Each module is responsible for learning a specific task, such as identifying sentiment in text or identifying patterns in data. The modules are then combined to form a single neural network that can perform multiple tasks. In the context of news feed sentiment analysis, MNNs can be used to identify the sentiment of news articles, social media posts, and other forms of online content. This information can then be used to filter out irrelevant or unwanted content, to identify trends in public opinion, and to target users with relevant advertising. According to price forecasts for 3 Month period, the dominant strategy among neural network is: Sell

Key Points

1. How do you decide buy or sell a stock?
2. How useful are statistical predictions?
3. Can stock prices be predicted?

HXT:TSX Target Price Prediction Modeling Methodology

We consider Horizons S&P/TSX 60 Index ETF Decision Process with Modular Neural Network (Market News Sentiment Analysis) where A is the set of discrete actions of HXT:TSX 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= $\begin{array}{cccc}{p}_{\mathrm{a}1}& p_{\mathrm{a}2}& \dots & p_{1n}\\ & ⋮\\ p_{j1}& p_{j2}& \dots & p_{jn}\\ & ⋮\\ p_{k1}& p_{k2}& \dots & p_{kn}\\ & ⋮\\ p_{n1}& p_{n2}& \dots & p_{nn}\end{array}$ X R(Modular Neural Network (Market News Sentiment Analysis)) X S(n):→ 3 Month $\overrightarrow{S}=\left(s_1,s_2,s_3\right)$

n:Time series to forecast

p:Price signals of HXT:TSX stock

j:Nash equilibria (Neural Network)

k:Dominated move

a:Best response for target price

Modular Neural Network (Market News Sentiment Analysis)

A modular neural network (MNN) is a type of artificial neural network that can be used for news feed sentiment analysis. MNNs are made up of multiple smaller neural networks, called modules. Each module is responsible for learning a specific task, such as identifying sentiment in text or identifying patterns in data. The modules are then combined to form a single neural network that can perform multiple tasks. In the context of news feed sentiment analysis, MNNs can be used to identify the sentiment of news articles, social media posts, and other forms of online content. This information can then be used to filter out irrelevant or unwanted content, to identify trends in public opinion, and to target users with relevant advertising.

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?

HXT:TSX Stock Forecast (Buy or Sell)

Sample Set: Neural Network
Stock/Index: HXT:TSX Horizons S&P/TSX 60 Index ETF
Time series to forecast: 3 Month

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

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 Modular Neural Network (Market News Sentiment Analysis) based HXT:TSX Stock Prediction Model

1. In addition to those hedging relationships specified in paragraph 6.9.1, an entity shall apply the requirements in paragraphs 6.9.11 and 6.9.12 to new hedging relationships in which an alternative benchmark rate is designated as a non-contractually specified risk component (see paragraphs 6.3.7(a) and B6.3.8) when, because of interest rate benchmark reform, that risk component is not separately identifiable at the date it is designated.
2. The accounting for the time value of options in accordance with paragraph 6.5.15 applies only to the extent that the time value relates to the hedged item (aligned time value). The time value of an option relates to the hedged item if the critical terms of the option (such as the nominal amount, life and underlying) are aligned with the hedged item. Hence, if the critical terms of the option and the hedged item are not fully aligned, an entity shall determine the aligned time value, ie how much of the time value included in the premium (actual time value) relates to the hedged item (and therefore should be treated in accordance with paragraph 6.5.15). An entity determines the aligned time value using the valuation of the option that would have critical terms that perfectly match the hedged item.
3. When measuring a loss allowance for a lease receivable, the cash flows used for determining the expected credit losses should be consistent with the cash flows used in measuring the lease receivable in accordance with IFRS 16 Leases.
4. It would not be acceptable to designate only some of the financial assets and financial liabilities giving rise to the inconsistency as at fair value through profit or loss if to do so would not eliminate or significantly reduce the inconsistency and would therefore not result in more relevant information. However, it would be acceptable to designate only some of a number of similar financial assets or similar financial liabilities if doing so achieves a significant reduction (and possibly a greater reduction than other allowable designations) in the inconsistency. For example, assume an entity has a number of similar financial liabilities that sum to CU100 and a number of similar financial assets that sum to CU50 but are measured on a different basis. The entity may significantly reduce the measurement inconsistency by designating at initial recognition all of the assets but only some of the liabilities (for example, individual liabilities with a combined total of CU45) as at fair value through profit or loss. However, because designation as at fair value through profit or loss can be applied only to the whole of a financial instrument, the entity in this example must designate one or more liabilities in their entirety. It could not designate either a component of a liability (eg changes in value attributable to only one risk, such as changes in a benchmark interest rate) or a proportion (ie percentage) of a liability.

*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.

HXT:TSX Horizons S&P/TSX 60 Index ETF Financial Analysis*

Rating	Short-Term	Long-Term Senior
Outlook*	Ba1	B2
Income Statement	Baa2	B1
Balance Sheet	Ba3	Baa2
Leverage Ratios	Baa2	C
Cash Flow	Baa2	C
Rates of Return and Profitability	Caa2	C

*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

Horizons S&P/TSX 60 Index ETF is assigned short-term Ba1 & long-term B2 estimated rating. Horizons S&P/TSX 60 Index ETF prediction model is evaluated with Modular Neural Network (Market News Sentiment Analysis) and Wilcoxon Sign-Rank Test^1,2,3,4 and it is concluded that the HXT:TSX stock is predictable in the short/long term. According to price forecasts for 3 Month period, the dominant strategy among neural network is: Sell

Prediction Confidence Score

Trust metric by Neural Network: 83 out of 100 with 575 signals.

References

1. Clements, M. P. D. F. Hendry (1996), "Intercept corrections and structural change," Journal of Applied Econometrics, 11, 475–494.
2. Pennington J, Socher R, Manning CD. 2014. GloVe: global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods on Natural Language Processing, pp. 1532–43. New York: Assoc. Comput. Linguist.
3. Matzkin RL. 1994. Restrictions of economic theory in nonparametric methods. In Handbook of Econometrics, Vol. 4, ed. R Engle, D McFadden, pp. 2523–58. Amsterdam: Elsevier
4. Arora S, Li Y, Liang Y, Ma T. 2016. RAND-WALK: a latent variable model approach to word embeddings. Trans. Assoc. Comput. Linguist. 4:385–99
5. Robins J, Rotnitzky A. 1995. Semiparametric efficiency in multivariate regression models with missing data. J. Am. Stat. Assoc. 90:122–29
6. 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]
7. P. Artzner, F. Delbaen, J. Eber, and D. Heath. Coherent measures of risk. Journal of Mathematical Finance, 9(3):203–228, 1999

Frequently Asked Questions

Q: What is the prediction methodology for HXT:TSX stock?
A: HXT:TSX stock prediction methodology: We evaluate the prediction models Modular Neural Network (Market News Sentiment Analysis) and Wilcoxon Sign-Rank Test
Q: Is HXT:TSX stock a buy or sell?
A: The dominant strategy among neural network is to Sell HXT:TSX Stock.
Q: Is Horizons S&P/TSX 60 Index ETF stock a good investment?
A: The consensus rating for Horizons S&P/TSX 60 Index ETF is Sell and is assigned short-term Ba1 & long-term B2 estimated rating.
Q: What is the consensus rating of HXT:TSX stock?
A: The consensus rating for HXT:TSX is Sell.
Q: What is the prediction period for HXT:TSX stock?
A: The prediction period for HXT:TSX is 3 Month