John Kamwele Mutinda

Mr. John Kamwele Mutinda


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 September 2024 in Scientific African
Verified
Journal Article
Open access
JMJohn Kamwele Mutinda
John Kamwele Mutinda
Amos Kipkorir Langat,  Ph.D.Amos Kipkorir Langat, Ph.D.
Amos Kipkorir Langat, Ph.D.
The non-linear and non-stationary nature of financial time series data poses significant challenges for standalone statistical and neural network methods. While predictive modeling in finance often focuses on volatility, there is a notable lack of research on predicting actual stock prices, particularly in the African market. This study addresses this gap by utilizing Airtel stock data from Yahoo Finance, spanning June 28, 2019, to May 8, 2024. The research employs the GARCH model to extract statistical properties, which are then combined with historical prices and fed into LSTM, GRU, and Transformer models leading to GARCH-LSTM, GARCH-GRU, GARCH-Transfomer hybrid models. These hybrid models are benchmarked against standalone LSTM, GRU and Transfomer models using RMSE, MAE, MAPE, and R-squared metrics. Results indicate that hybrid models, especially GARCH-LSTM, significantly outperform standalone models. This integration of GARCH with advanced AI models offers a more robust framework for stock price prediction, enhancing accuracy and reliability in forecasting future prices.

1 January 2025 in Journal of Applied Mathematics
Verified
Journal Article
Open access
JMJohn Kamwele Mutinda
John Kamwele Mutinda
AGAbebe Geletu
Abebe Geletu
This study investigates the forecasting of the Deutscher Aktienindex (DAX) market index by addressing the nonlinear and nonstationary nature of financial time series data using the CEEMDAN decomposition method. The CEEMDAN technique is used to decompose the time series into intrinsic mode functions (IMFs) and residuals, which are classified into low‐frequency (LF), medium‐frequency (MF), and high‐frequency (HF) components. Long short‐term memory (LSTM) networks are applied to the MF and HF components, while the backpropagation neural network (BPNN) is utilized for the LF components, resulting in a robust hybrid model termed CEEMDAN‐LSTM‐BPNN. To evaluate the performance of the proposed model, we compare it against several benchmark models, including ARIMA, RNN, LSTM, GRU, BIGRU, BILSTM, BPNN, CEEMDAN‐LSTM, CEEMDAN‐GRU, CEEMDAN‐BPNN, and CEEMDAN‐GRU‐BPNN, across different training–testing splits (70% training/30% testing, 80% training/20% testing, and 90% training/10% testing). The model’s predictive accuracy is measured using six metrics: root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), symmetric mean absolute percentage error (SMAPE), root mean squared logarithmic error (RMSLE), and R ‐squared. To further assess model performance, we conduct the Diebold–Mariano (DM) test to compare forecast accuracy between the proposed and benchmark models and the model confidence set (MCS) test to evaluate the statistical significance of the improvement. The results demonstrate that the CEEMDAN‐LSTM‐BPNN model significantly outperforms other methods in terms of accuracy, with the DM and MCS tests confirming the superiority of the proposed model across multiple evaluation metrics. The findings highlight the importance of combining advanced decomposition methods and deep learning models for financial forecasting. This research contributes to the development of more accurate forecasting techniques, offering valuable implications for financial decision‐making and risk management.

1 January 2025 in International Journal of Mathematics and Mathematical Sciences
Verified
Journal Article
Open access
JMJohn Kamwele Mutinda
John Kamwele Mutinda
Amos Kipkorir Langat,  Ph.D.Amos Kipkorir Langat, Ph.D.
Amos Kipkorir Langat, Ph.D.
SMSamuel Mwalili
Samuel Mwalili
Accurate temperature forecasting is of paramount importance across various sectors, influencing decision‐making processes and impacting numerous aspects of daily life. This study analyzes temperature time series data from the Nairobi County in Kenya, aiming to develop accurate hybrid time series forecasting models. Initial statistical tests revealed significant nonstationarity and nonlinearity in the data, prompting the adoption of specialized modeling techniques. Using variational mode decomposition (VMD), the raw time series was decomposed into interpretable components, enhancing feature representation and understanding of temperature dynamics. Hybrid forecasting models were then constructed by integrating VMD with both statistical (autoregressive integrated moving average [ARIMA]) and deep learning (gated recurrent unit [GRU], long short‐term memory [LSTM], and Transformer) architectures. Evaluation metrics, including root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and R ‐squared, highlighted the superiority of hybrid models over individual approaches, particularly those combining VMD with ARIMA, GRU, LSTM, and Transformer. The experimental results for temperature prediction show that the hybrid models combining VMD with statistical and deep learning networks achieved improved forecasting accuracy compared with baseline models. Specifically, the VMD–ARIMA–GRU model emerged as the top performer, demonstrating the lowest error metrics and highest explanatory power. With a low RMSE of 0.710090, MAE of 0.561726, and MAPE of 2.808193%, the model demonstrates remarkable accuracy in predicting temperature values. In addition, the high R‐squared value of 0.779234 indicates that approximately 77.92% of the variance in the observed data is explained by the model, showcasing its robustness and effectiveness in capturing the underlying patterns in temperature time series data. Overall, this study underscores the importance of VMD in preprocessing data to enhance feature representation and forecasting accuracy. By combining statistical and deep learning methods, hybrid models incorporating VMD offer a comprehensive solution for accurate temperature prediction, with implications for climate modeling and environmental monitoring.

23 February 2024 in Asian Journal of Research in Computer Science
Verified
Journal Article
Open access
PDF file
JMJohn Kamwele Mutinda
John Kamwele Mutinda
ALAmos Kipkorir Langat
Amos Kipkorir Langat
In this study, we delve into the pivotal role of dimension reduction techniques in influencing the performance of machine learning algorithms for heart disease prediction. Through a comprehensive exploration of a dataset encompassing crucial features such as age, sex, chest pain type, blood pressure, cholesterol levels, and more, we investigate the impact of different techniques—namely, Principal Component Analysis (PCA), Kernel Principal Component Analysis (KPCA), and Linear Discriminant Analysis (LDA) on classification algorithm effectiveness. The classification algorithms considered were Logistic Regression, Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Naive Bayes, and Deep Neural Network (DNN). We used K-fold cross validation to train and validate the classification algorithms. The performance of these algorithms was assessed using a range of key metrics including accuracy, F1-score, precision, recall, and specificity. The results reveals that Linear Discriminant Analysis consistently emerged as a potent method, remarkably enhancing algorithm performance across all assessed metrics. We also identified Naive Bayes and Logistic Regression as standout algorithms, demonstrating remarkable resilience and reliability across diverse scenarios. These findings collectively shed light on the intricate interplay between dimension reduction techniques and algorithm selection, offering critical insights for crafting more accurate and robust strategies in the prediction of heart disease.

18 June 2025 in Computational Economics
Verified
Journal Article
Closed access
PDF file
JMJohn Kamwele Mutinda
John Kamwele Mutinda
YLyong li
yong li

1 January 2025 in International Journal of Mathematics and Mathematical Sciences
Verified
Journal Article
Open access
JMJohn Kamwele Mutinda
John Kamwele Mutinda
Amos Kipkorir Langat,  Ph.D.Amos Kipkorir Langat, Ph.D.
Amos Kipkorir Langat, Ph.D.
SMSamuel Mwalili
Samuel Mwalili
Stock price forecasting is complex due to the nonlinear and nonstationary nature of financial time series. This study proposes a hybrid variational mode decomposition (VMD)–generalized autoregressive conditional heteroskedasticity (GARCH)–long short‐term memory (LSTM) model to predict Airtel’s stock prices, integrating VMD, GARCH, and LSTM networks. VMD decomposes the stock price series into intrinsic mode functions (IMFs), enabling frequency‐specific modeling. High‐frequency IMFs, which exhibit volatility, are processed with GARCH to capture time‐varying volatility and are then fed into LSTM to model residual nonlinear dynamics. Low‐frequency IMFs, which reflect smoother trends, are directly modeled by LSTM. Final forecasts are aggregated via an additive ensemble. Initially evaluated on an 80:20 train–test split, the model underwent robustness checks with 70:30 and 90:10 splits, consistently outperforming benchmark models: transformer, GRU, LSTM, BiGRU, BiLSTM, VMD‐transformer, VMD‐GRU, VMD‐LSTM, VMD‐BiGRU, VMD‐BiLSTM, VMD‐GARCH‐transformer, VMD‐GARCH‐GRU, VMD‐GARCH‐BiGRU, and VMD‐GARCH‐BiLSTM. Diebold–Mariano tests confirmed statistical superiority across MSE, MAE, and MAPE loss functions, validating the model’s enhanced accuracy. These robustness checks demonstrate the model’s stability across varied data partitions, offering investors a reliable tool for risk mitigation. By effectively addressing volatility and nonlinearity, this hybrid framework advances financial forecasting, enhances decision‐making in dynamic financial stocks, and contributes to robust time‐series prediction methodologies.