Outlook: BAK Braskem SA ADR is assigned short-term B1 & long-term B1 estimated rating.
AUC Score : What is AUC Score?
Short-Term Revised1 :
Time series to forecast n: for Weeks2
Methodology : Transductive Learning (ML)
Hypothesis Testing : ElasticNet Regression
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.

## Key Points

1. Transductive Learning (ML) for BAK stock price prediction process.
2. ElasticNet Regression
3. Fundemental Analysis with Algorithmic Trading
4. Can stock prices be predicted?
5. What are buy sell or hold recommendations?

## BAK Stock Price Forecast

We consider Braskem SA ADR Decision Process with Transductive Learning (ML) where A is the set of discrete actions of BAK 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

Sample Set: Neural Network
Time series to forecast: 16 Weeks

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

F(ElasticNet Regression)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(Transductive Learning (ML)) X S(n):→ 16 Weeks $∑ i = 1 n r i$

n:Time series to forecast

p:Price signals of BAK stock

j:Nash equilibria (Neural Network)

k:Dominated move of BAK stock holders

a:Best response for BAK target price

Transductive learning is a supervised machine learning (ML) method in which the model is trained on both labeled and unlabeled data. The goal of transductive learning is to predict the labels of the unlabeled data. Transductive learning is a hybrid of inductive and semi-supervised learning. Inductive learning algorithms are trained on labeled data only, while semi-supervised learning algorithms are trained on a combination of labeled and unlabeled data. Transductive learning algorithms can achieve better performance than inductive learning algorithms on tasks where there is a small amount of labeled data. This is because transductive learning algorithms can use the unlabeled data to help them learn the relationships between the features and the labels.5 Elastic net regression is a type of regression analysis that combines the benefits of ridge regression and lasso regression. It is a regularized regression method that adds a penalty to the least squares objective function in order to reduce the variance of the estimates, induce sparsity in the model, and reduce overfitting. This is done by adding a term to the objective function that is proportional to the sum of the squares of the coefficients and the sum of the absolute values of the coefficients. The penalty terms are controlled by two parameters, called the ridge constant and the lasso constant. Elastic net regression can be used to address the problems of multicollinearity, overfitting, and sensitivity to outliers. It is a more flexible method than ridge regression or lasso regression, and it can often achieve better results.6,7

For further technical information as per how our model work we invite you to visit the article below:

How do PredictiveAI algorithms actually work?

### BAK Stock Forecast (Buy or Sell) Strategic Interaction Table

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%

Rating Short-Term Long-Term Senior
Outlook*B1B1
Income StatementBaa2B1
Balance SheetCaa2B3
Leverage RatiosB3Ba1
Cash FlowCB1
Rates of Return and ProfitabilityBaa2C

*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?

## References

1. V. Borkar. An actor-critic algorithm for constrained Markov decision processes. Systems & Control Letters, 54(3):207–213, 2005.
2. Lai TL, Robbins H. 1985. Asymptotically efficient adaptive allocation rules. Adv. Appl. Math. 6:4–22
3. C. Wu and Y. Lin. Minimizing risk models in Markov decision processes with policies depending on target values. Journal of Mathematical Analysis and Applications, 231(1):47–67, 1999
4. Athey S. 2017. Beyond prediction: using big data for policy problems. Science 355:483–85
5. Andrews, D. W. K. W. Ploberger (1994), "Optimal tests when a nuisance parameter is present only under the alternative," Econometrica, 62, 1383–1414.
6. Bessler, D. A. R. A. Babula, (1987), "Forecasting wheat exports: Do exchange rates matter?" Journal of Business and Economic Statistics, 5, 397–406.
7. Dietterich TG. 2000. Ensemble methods in machine learning. In Multiple Classifier Systems: First International Workshop, Cagliari, Italy, June 21–23, pp. 1–15. Berlin: Springer