PSEi Composite index seen cautiously optimistic.

Outlook: PSEi Composite index is assigned short-term B2 & long-term B2 estimated rating.
AUC Score : What is AUC Score?
Short-term Tactic¹ :
Dominant Strategy :
Time series to forecast n: for Weeks²
ML Model Testing : Modular Neural Network (CNN Layer)
Hypothesis Testing : Pearson Correlation
Surveillance : Major exchange and OTC

¹Short-term revised.

²Time series is updated based on short-term trends.

Key Points

The PSEi Composite index is expected to experience moderate growth, driven by strong domestic consumption and a recovering tourism sector, though this positive momentum may be tempered by persistent inflation concerns and potential interest rate hikes by the central bank, possibly leading to a slowdown in certain sectors. Risks include global economic uncertainties stemming from geopolitical tensions and fluctuating commodity prices, which could negatively impact investor sentiment and lead to increased market volatility; further challenges could arise from unforeseen domestic policy changes and potential delays in infrastructure projects, potentially diminishing market confidence and growth prospects.

About PSEi Composite Index

This exclusive content is only available to premium users.

PSEi Composite Index Forecasting Model

Our team of data scientists and economists proposes a machine learning model designed to forecast the Philippine Stock Exchange Index (PSEi) Composite. The model leverages a diverse range of predictor variables categorized into three primary groups: economic indicators, market sentiment measures, and technical analysis metrics. Economic indicators will include crucial data points such as GDP growth, inflation rates, interest rate changes (BSP policy rate), manufacturing activity (PMI), and foreign direct investment (FDI). Market sentiment will be gauged through Philippine-specific consumer confidence indices, business confidence indices, and publicly available sentiment data derived from social media trends related to the stock market. Finally, technical indicators will incorporate historical PSEi performance data including moving averages (MA), relative strength index (RSI), trading volume, and volatility measures (e.g., VIX equivalent). This comprehensive approach aims to capture the multifaceted influences that drive stock market behavior.

The model's architecture will employ a supervised learning approach, initially testing and comparing several algorithms. We will consider time series models such as ARIMA (Autoregressive Integrated Moving Average) and its variations (SARIMA) for capturing the inherent temporal dependencies in the PSEi data. Furthermore, we will evaluate advanced machine learning methods, including Recurrent Neural Networks (RNNs), particularly Long Short-Term Memory (LSTM) networks, due to their ability to handle sequential data and capture long-range dependencies. For feature engineering and selection, we will conduct rigorous exploratory data analysis (EDA) to identify relevant variables and handle missing data. Feature scaling techniques, such as standardization, will be applied to ensure all predictors contribute equally. Model performance will be rigorously evaluated using metrics like Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared. A holdout validation set and potentially cross-validation will be employed to assess the model's generalization capability and prevent overfitting.

The forecasting horizon will be set for short-term predictions (e.g., daily or weekly). The model's output will consist of predicted PSEi values (or changes in the index value) along with associated confidence intervals. To mitigate potential limitations, we plan to regularly retrain the model with new data to adapt to evolving market dynamics and incorporate updated economic data. We will also perform sensitivity analysis to gauge the impact of specific predictor variables on the forecast and conduct error analysis to investigate the sources of prediction inaccuracies. The model's output will be integrated into a user-friendly dashboard providing visualizations, forecasts, and potential trading signals. The model's final output will assist investment and economic strategy.

ML Model Testing

F(Pearson Correlation)^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 (CNN Layer))^3,4,5 X S(n):→ 6 Month $\sum _{i=1}^n\left(a_i\right)$

n:Time series to forecast

p:Price signals of PSEi Composite index

j:Nash equilibria (Neural Network)

k:Dominated move of PSEi Composite index holders

a:Best response for PSEi Composite target price

 

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

How do KappaSignal algorithms actually work?

PSEi Composite Index Forecast 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%

Philippine Stock Exchange (PSEi) Composite Index: Financial Outlook and Forecast

The Philippine Stock Exchange index (PSEi), a critical barometer of the country's economic health, is currently navigating a complex landscape influenced by both domestic and global factors. Recent performance reflects a period of consolidation following a period of growth, indicating a degree of caution among investors. Key sectors, including banking, property, and telecommunications, continue to exhibit significant influence on the overall index performance. Government initiatives aimed at infrastructure development and fiscal reforms are providing a supportive backdrop, stimulating activity in related industries and contributing to investor sentiment. However, the persistent challenge of inflation, both globally and locally, and its impact on interest rate decisions by the Bangko Sentral ng Pilipinas (BSP) remains a crucial factor shaping market expectations. Furthermore, the geopolitical uncertainties and their effects on global supply chains, as well as commodity prices are also contributing to the dynamics of the stock market.

The financial outlook for the PSEi is intricately linked to the performance of the Philippine economy and the broader global environment. Strong domestic consumption, driven by a large and increasingly affluent population, is a fundamental driver of growth. Investments in infrastructure projects, designed to improve connectivity and boost economic productivity, are expected to attract further foreign direct investment (FDI) and stimulate local business expansion. Moreover, the tourism sector is recovering from the setbacks of the pandemic and will be a key contributor to the economy. On the global front, the stability of major economies such as the United States and China and their respective economic performances influence the trading sentiment. The pace of the US Federal Reserve's monetary policy tightening and its impact on global liquidity is a central concern for investors. Investors are carefully monitoring the trends in global commodity prices because fluctuations in oil, metal and agricultural products have direct effects on some Philippine industries.

Looking ahead, the PSEi is likely to exhibit a relatively moderate growth trajectory. This outlook is based on the expectation of continued economic expansion, driven by government spending, robust domestic consumption, and the gradual recovery of key sectors. Corporate earnings are projected to improve, reflecting increased economic activity and improved operational efficiency. However, several challenges could moderate the pace of growth. Persistently high inflation and further interest rate hikes could dampen consumer spending and increase borrowing costs for businesses, impacting profitability. Geopolitical risks and their potential to disrupt global trade flows and supply chains pose another significant threat. The government's ability to effectively implement reforms and maintain fiscal discipline will be a key determinant of investor confidence. Any unforeseen downturns in the global economy, especially from the US and China, could have a negative impact on the Philippine markets.

Overall, the forecast for the PSEi is cautiously optimistic, with a moderate positive trajectory anticipated in the coming period. The primary risk to this prediction is the persistent inflationary pressures and the ensuing possibility of more stringent monetary policies which could severely dampen economic activity. Geopolitical instability, which could disrupt trade and increase commodity prices, constitutes a significant external risk. Conversely, the potential for stronger-than-expected economic growth driven by infrastructure investments, successful reform implementation, and continued domestic consumption could contribute to a better performance. Therefore, investors should adopt a balanced approach, incorporating both upside potential and downside risks into their investment strategies, while staying informed on economic and political developments both locally and internationally.

Rating	Short-Term	Long-Term Senior
Outlook	B2	B2
Income Statement	B1	C
Balance Sheet	C	B2
Leverage Ratios	B3	Baa2
Cash Flow	C	Caa2
Rates of Return and Profitability	Baa2	B3

*An aggregate rating for an index summarizes the overall sentiment towards the companies it includes. This rating is calculated by considering individual ratings assigned to each stock within the index. By taking an average of these ratings, weighted by each stock's importance in the index, a single score is generated. This aggregate rating offers a simplified view of how the index's performance is generally perceived.
How does neural network examine financial reports and understand financial state of the company?

References

1. Hill JL. 2011. Bayesian nonparametric modeling for causal inference. J. Comput. Graph. Stat. 20:217–40
2. J. G. Schneider, W. Wong, A. W. Moore, and M. A. Riedmiller. Distributed value functions. In Proceedings of the Sixteenth International Conference on Machine Learning (ICML 1999), Bled, Slovenia, June 27 - 30, 1999, pages 371–378, 1999.
3. E. Collins. Using Markov decision processes to optimize a nonlinear functional of the final distribution, with manufacturing applications. In Stochastic Modelling in Innovative Manufacturing, pages 30–45. Springer, 1997
4. Varian HR. 2014. Big data: new tricks for econometrics. J. Econ. Perspect. 28:3–28
5. M. Babes, E. M. de Cote, and M. L. Littman. Social reward shaping in the prisoner's dilemma. In 7th International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS 2008), Estoril, Portugal, May 12-16, 2008, Volume 3, pages 1389–1392, 2008.
6. Holland PW. 1986. Statistics and causal inference. J. Am. Stat. Assoc. 81:945–60
7. M. Babes, E. M. de Cote, and M. L. Littman. Social reward shaping in the prisoner's dilemma. In 7th International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS 2008), Estoril, Portugal, May 12-16, 2008, Volume 3, pages 1389–1392, 2008.