The nature of stock market movement has always been ambiguous for investors because of various influential factors. This study aims to significantly reduce the risk of trend prediction with machine learning and deep learning algorithms.** We evaluate BIST 100 Index prediction models with Modular Neural Network (DNN Layer) and Logistic Regression ^{1,2,3,4} and conclude that the BIST 100 Index stock is predictable in the short/long term. **

**According to price forecasts for (n+6 month) period: The dominant strategy among neural network is to Sell BIST 100 Index stock.**

**BIST 100 Index, BIST 100 Index, stock forecast, machine learning based prediction, risk rating, buy-sell behaviour, stock analysis, target price analysis, options and futures.**

*Keywords:*## Key Points

- Can we predict stock market using machine learning?
- Fundemental Analysis with Algorithmic Trading
- Should I buy stocks now or wait amid such uncertainty?

## BIST 100 Index Target Price Prediction Modeling Methodology

Stock market trading is an activity in which investors need fast and accurate information to make effective decisions. Since many stocks are traded on a stock exchange, numerous factors influence the decision-making process. Moreover, the behaviour of stock prices is uncertain and hard to predict. For these reasons, stock price prediction is an important process and a challenging one. We consider BIST 100 Index Stock Decision Process with Logistic Regression where A is the set of discrete actions of BIST 100 Index 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(Logistic 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(Modular Neural Network (DNN Layer)) X S(n):→ (n+6 month) $\overrightarrow{R}=\left({r}_{1},{r}_{2},{r}_{3}\right)$

n:Time series to forecast

p:Price signals of BIST 100 Index 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?

## BIST 100 Index Stock Forecast (Buy or Sell) for (n+6 month)

**Sample Set:**Neural Network

**Stock/Index:**BIST 100 Index BIST 100 Index

**Time series to forecast n: 28 Oct 2022**for (n+6 month)

**According to price forecasts for (n+6 month) period: The dominant strategy among neural network is to Sell BIST 100 Index 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 BIST 100 Index

- An entity shall apply Prepayment Features with Negative Compensation (Amendments to IFRS 9) retrospectively in accordance with IAS 8, except as specified in paragraphs 7.2.30–7.2.34
- Annual Improvements to IFRS Standards 2018–2020, issued in May 2020, added paragraphs 7.2.35 and B3.3.6A and amended paragraph B3.3.6. An entity shall apply that amendment for annual reporting periods beginning on or after 1 January 2022. Earlier application is permitted. If an entity applies the amendment for an earlier period, it shall disclose that fact.
- An entity may manage and evaluate the performance of a group of financial liabilities or financial assets and financial liabilities in such a way that measuring that group at fair value through profit or loss results in more relevant information. The focus in this instance is on the way the entity manages and evaluates performance, instead of on the nature of its financial instruments.
- IFRS 7 defines credit risk as 'the risk that one party to a financial instrument will cause a financial loss for the other party by failing to discharge an obligation'. The requirement in paragraph 5.7.7(a) relates to the risk that the issuer will fail to perform on that particular liability. It does not necessarily relate to the creditworthiness of the issuer. For example, if an entity issues a collateralised liability and a non-collateralised liability that are otherwise identical, the credit risk of those two liabilities will be different, even though they are issued by the same entity. The credit risk on the collateralised liability will be less than the credit risk of the non-collateralised liability. The credit risk for a collateralised liability may be close to zero.

*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

BIST 100 Index assigned short-term B2 & long-term Ba3 forecasted stock rating.** We evaluate the prediction models Modular Neural Network (DNN Layer) with Logistic Regression ^{1,2,3,4} and conclude that the BIST 100 Index stock is predictable in the short/long term.**

**According to price forecasts for (n+6 month) period: The dominant strategy among neural network is to Sell BIST 100 Index stock.**

### Financial State Forecast for BIST 100 Index BIST 100 Index Stock Options & Futures

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

Outlook* | B2 | Ba3 |

Operational Risk | 79 | 42 |

Market Risk | 77 | 76 |

Technical Analysis | 55 | 56 |

Fundamental Analysis | 40 | 64 |

Risk Unsystematic | 30 | 73 |

### Prediction Confidence Score

## References

- Andrews, D. W. K. (1993), "Tests for parameter instability and structural change with unknown change point," Econometrica, 61, 821–856.
- Breiman L. 1993. Better subset selection using the non-negative garotte. Tech. Rep., Univ. Calif., Berkeley
- Blei DM, Lafferty JD. 2009. Topic models. In Text Mining: Classification, Clustering, and Applications, ed. A Srivastava, M Sahami, pp. 101–24. Boca Raton, FL: CRC Press
- D. White. Mean, variance, and probabilistic criteria in finite Markov decision processes: A review. Journal of Optimization Theory and Applications, 56(1):1–29, 1988.
- D. Bertsekas. Dynamic programming and optimal control. Athena Scientific, 1995.
- 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
- Schapire RE, Freund Y. 2012. Boosting: Foundations and Algorithms. Cambridge, MA: MIT Press

## Frequently Asked Questions

Q: What is the prediction methodology for BIST 100 Index stock?A: BIST 100 Index stock prediction methodology: We evaluate the prediction models Modular Neural Network (DNN Layer) and Logistic Regression

Q: Is BIST 100 Index stock a buy or sell?

A: The dominant strategy among neural network is to Sell BIST 100 Index Stock.

Q: Is BIST 100 Index stock a good investment?

A: The consensus rating for BIST 100 Index is Sell and assigned short-term B2 & long-term Ba3 forecasted stock rating.

Q: What is the consensus rating of BIST 100 Index stock?

A: The consensus rating for BIST 100 Index is Sell.

Q: What is the prediction period for BIST 100 Index stock?

A: The prediction period for BIST 100 Index is (n+6 month)