MPC Stock Forecast

Outlook: MPC is assigned short-term B2 & long-term B1 estimated rating.
AUC Score : What is AUC Score?
Short-term Tactic¹ :
Dominant Strategy :
Time series to forecast n: for Weeks²
ML Model Testing : Multi-Task Learning (ML)
Hypothesis Testing : Sign Test
Surveillance : Major exchange and OTC

¹Short-term revised.

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

Key Points

This exclusive content is only available to premium users.

About MPC

This exclusive content is only available to premium users.

Marathon Petroleum Corporation (MPC) Stock Forecasting Model

This document outlines the development of a machine learning model designed for forecasting Marathon Petroleum Corporation (MPC) common stock performance. Our approach leverages a combination of econometric principles and advanced machine learning techniques to capture the multifaceted drivers influencing stock prices. The initial phase of model development involves extensive data collection and preprocessing. This includes historical stock data, fundamental financial indicators such as revenue, earnings, and debt levels, as well as macroeconomic variables like oil prices, interest rates, and inflation. We will also incorporate relevant industry-specific data and news sentiment analysis to provide a comprehensive view of market dynamics. Rigorous data cleaning, feature engineering, and selection will be performed to ensure the robustness and predictive power of the model.

For the core predictive engine, we propose utilizing a hybrid model architecture. This will likely involve a combination of time-series models, such as ARIMA or Prophet, to capture inherent temporal patterns and seasonality, and more sophisticated machine learning algorithms like Recurrent Neural Networks (RNNs), specifically Long Short-Term Memory (LSTM) networks, or Gradient Boosting Machines (GBMs) like XGBoost. These advanced models are adept at learning complex, non-linear relationships within the data, which are crucial for accurately forecasting stock movements. The model will be trained on historical data, with a significant portion reserved for validation and out-of-sample testing to assess its generalization capabilities and mitigate overfitting. Performance will be evaluated using metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and directional accuracy.

The ultimate objective is to create a predictive tool that can provide actionable insights for investment decisions related to Marathon Petroleum Corporation. The model will aim to forecast short-to-medium term stock price trends, identifying potential opportunities and risks. Continuous monitoring and re-training of the model will be essential to adapt to evolving market conditions and maintain its accuracy over time. Furthermore, interpretability will be a key consideration, employing techniques such as feature importance analysis from GBMs or attention mechanisms in LSTMs, to understand the underlying factors driving the model's predictions. This will enhance confidence in the forecast and allow for more informed strategic planning.

ML Model Testing

F(Sign Test)^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(Multi-Task Learning (ML))^3,4,5 X S(n):→ 8 Weeks $R=\left(\begin{array}{ccc}1& 0& 0\\ 0& 1& 0\\ 0& 0& 1\end{array}\right)$

n:Time series to forecast

p:Price signals of MPC stock

j:Nash equilibria (Neural Network)

k:Dominated move of MPC stock holders

a:Best response for MPC 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?

MPC 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%

This exclusive content is only available to premium users.

Rating	Short-Term	Long-Term Senior
Outlook	B2	B1
Income Statement	Ba3	Ba3
Balance Sheet	C	Caa2
Leverage Ratios	Ba1	Ba1
Cash Flow	B1	C
Rates of Return and Profitability	B3	Baa2

*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. Varian HR. 2014. Big data: new tricks for econometrics. J. Econ. Perspect. 28:3–28
2. Chernozhukov V, Chetverikov D, Demirer M, Duflo E, Hansen C, Newey W. 2017. Double/debiased/ Neyman machine learning of treatment effects. Am. Econ. Rev. 107:261–65
3. Jorgenson, D.W., Weitzman, M.L., ZXhang, Y.X., Haxo, Y.M. and Mat, Y.X., 2023. Can Neural Networks Predict Stock Market?. AC Investment Research Journal, 220(44).
4. Kallus N. 2017. Balanced policy evaluation and learning. arXiv:1705.07384 [stat.ML]
5. Friedman JH. 2002. Stochastic gradient boosting. Comput. Stat. Data Anal. 38:367–78
6. Jorgenson, D.W., Weitzman, M.L., ZXhang, Y.X., Haxo, Y.M. and Mat, Y.X., 2023. Tesla Stock: Hold for Now, But Watch for Opportunities. AC Investment Research Journal, 220(44).
7. S. J. Russell and A. Zimdars. Q-decomposition for reinforcement learning agents. In Machine Learning, Proceedings of the Twentieth International Conference (ICML 2003), August 21-24, 2003, Washington, DC, USA, pages 656–663, 2003.