-
Research Article
Forecasting Stock Prices Using Heston-Artificial Neural Network Model
Ann Maina,
Samuel Mwalili,
Bonface Malenje
Issue:
Volume 9, Issue 2, April 2023
Pages:
22-33
Received:
13 September 2023
Accepted:
4 October 2023
Published:
28 October 2023
Abstract: Considering the evolution of financial globalization and the impacts of the global economic crisis, stock trading faces unprecedented fluctuations. The inherent volatility in stock prices has resulted in market uncertainty, prompting an interest among investors in reliable pricing models in order to maximize profits. To this end, researchers have continued to diligently refine stock pricing models to mitigate market uncertainty. One notable contender in this arena is the Heston model, conceived to remedy the limitations of the Black-Scholes model. The model embraces stochastic volatility, a departure from the constant volatility assumption underpinning the Black-Scholes model. However, the Heston model itself grapples with certain pivotal constraints, mainly the requisite precision in parameter calibration to produce a reliable estimate. Leveraging the current wave of technological advancement, this study uses an Artificial Neural Network (ANN) as a substitute for simulating different volatility parameters in the Heston model. This approach culminates in the construction of a hybrid semi-parametric forecasting model termed the Heston-ANN model. The study applies this model to datasets of three distinct stocks: BA, IBM, and GOLD. Through graphical analysis and the evaluation of different model performance metrics including Mean Absolute Percentage Error, Mean Absolute Error, and Mean Squared Error, the study compares the hybrid model to the original Heston model. The results reveal that the Heston-ANN model yields more accurate forecasts when juxtaposed with its precursor, the original Heston model. The synergy between the Heston model and ANN makes the hybrid model a more robust solution for forecasting stock prices.
Abstract: Considering the evolution of financial globalization and the impacts of the global economic crisis, stock trading faces unprecedented fluctuations. The inherent volatility in stock prices has resulted in market uncertainty, prompting an interest among investors in reliable pricing models in order to maximize profits. To this end, researchers have c...
Show More
-
Research Article
Modeling and Forecasting the Domestic Retail Price of Teff in Ethiopia
Issue:
Volume 9, Issue 2, April 2023
Pages:
34-42
Received:
24 September 2023
Accepted:
10 October 2023
Published:
28 October 2023
Abstract: One of the most popular main food crops grown by the majority of Ethiopians is teff (Eragrostis teff). More than 90% of the teff consumed worldwide is grown in Ethiopia. Despite having the highest output volume, this Ethiopian cereal crop has the highest price. The major goal of this study was to estimate and predict the domestic retail price of teff in Ethiopia. The Central Statistical Agency (CSA) of Ethiopia provided the data. The average monthly domestic retail price of teff per kilogram (in birr) in Ethiopia from January 1996 to June 2023 served as the study's source of data. The data are analyzed using both descriptive and inferential statistical methods. The Statistical Packages for Social Science (SPSS Version 20.0) and R statistical tools were used to conduct the analysis. Seasonal Autoregressive Integrated Moving Average (SARIMA) model was used for modeling the average monthly domestic retail price data of teff for 27 years and forecasting for the next five years. The final model chosen, using the AIC and BIC selection criteria, was SARIMA (2, 1, 4) × (0, 0, 2)12, which had the minimum Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The domestic retail price of teff in Ethiopia is therefore predicted to increase relatively rapidly over the next five years, with seasonal variation. The results of this study may contribute further to the policy discussion on lowering teff prices domestically and enhancing food security. Additionally, the study is very important for managing price instability for producers, consumers, wholesalers, and national agricultural pricing policy reforms. This study also provides evidence for government policymakers on the issue of Ethiopia's exorbitant cost of living and price inflation.
Abstract: One of the most popular main food crops grown by the majority of Ethiopians is teff (Eragrostis teff). More than 90% of the teff consumed worldwide is grown in Ethiopia. Despite having the highest output volume, this Ethiopian cereal crop has the highest price. The major goal of this study was to estimate and predict the domestic retail price of te...
Show More
-
Research Article
Bayesian Kernel Machine Analysis of Communicable Diseases Distribution in Machakos County, Kenya
Cecilia Mbithe Titus,
Anthony Wanjoya,
Thomas Mageto
Issue:
Volume 9, Issue 2, April 2023
Pages:
43-49
Received:
21 September 2023
Accepted:
20 October 2023
Published:
31 October 2023
Abstract: Effective management and control of communicable diseases are paramount for healthcare managers. Data-driven analysis plays a crucial role in understanding and curbing the spread of such diseases. While numerous epidemiological models have been developed to explain disease spread, many lack the incorporation of prior and posterior probabilities. In this research, we introduce a novel model called BKMR, designed to analyze and predict communicable disease occurrences in Machakos County. This study underscores the significance of data-driven approaches and outlines a plan to evaluate prediction accuracy through empirical analysis, with a particular focus on comparing BKMR with existing models using the R statistical software. We highlight the differences between estimated parameters and actual observations, emphasizing aspects not present in the training dataset. Our findings demonstrate that BKMR outperforms the Poisson regression model, offering greater flexibility and robustness. Moreover, it provides the ability to quantify uncertainty in model parameters, enhancing the capacity to make inferences about the real world. This research has substantial implications for healthcare management and disease control efforts in Machakos County.
Abstract: Effective management and control of communicable diseases are paramount for healthcare managers. Data-driven analysis plays a crucial role in understanding and curbing the spread of such diseases. While numerous epidemiological models have been developed to explain disease spread, many lack the incorporation of prior and posterior probabilities. In...
Show More
