International Journal of Innovative Research and Scientific Studies

Comparative analysis of the forecasting ability of AI and Arima models for the Vn-index

Pham Dan Khanh — 2026-02-03

This study compares the forecasting performance of a traditional econometric model (ARIMA) and artificial intelligence (AI)-based models, namely Multilayer Perceptron (MLP) and Extreme Gradient Boosting (XGBoost), in predicting the VN-Index during the period from 2015 to June 2025, which was characterized by heightened volatility in Vietnam’s stock market. Daily VN-Index closing prices were employed and divided into an 80% training set and a 20% testing set for out-of-sample evaluation. Forecast accuracy was assessed using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The Diebold–Mariano test was further applied to examine the statistical significance of differences in predictive performance among the models. The results indicate that ARIMA produced the highest forecasting errors, reflecting its limitations in capturing nonlinear dynamics and market volatility. The MLP model significantly improved forecasting accuracy, while XGBoost achieved the lowest error values across all evaluation metrics, demonstrating superior performance in handling noisy and volatile financial time series. AI-based models, particularly XGBoost, outperform the traditional ARIMA model in forecasting the VN-Index during volatile periods. The findings provide useful insights for investors and financial analysts by highlighting the effectiveness of advanced machine learning models in improving short-term market forecasting and investment decision-making in emerging markets.

Lightweight transformer models for scalable phishing email detection: A comparative study of ALBERT and TinyBERT on a balanced email corpus

Oladayo Atanda — 2026-02-03

Phishing is still a prominent threat to cybersecurity and takes advantage of user trust by sending malicious emails to capture credentials or install malware. Classical machine learning methods have not been able to keep pace with the changing sophistication of phishing content. This work introduces a thorough assessment of two Transformer-based models—ALBERT-base-v2 and TinyBERT—for phishing email classification. Utilizing a real-world dataset downloaded from Kaggle, both models were fine-tuned and compared according to performance measures such as accuracy, precision, recall, F1-score, and ROC-AUC. ALBERT achieved 97.54% in the test and a ROC-AUC of 0.997, whereas TinyBERT achieved 95.42% and a ROC-AUC of 0.992. The results from both models outperform some recent state-of-the-art approaches and validate the practical applicability of lightweight Transformers for cybersecurity use cases. While ALBERT provides better performance for cloud-based applications, TinyBERT provides significant computational efficiency that is suitable for real-time and resource-limited deployments. Recommendations are made for improving adversarial robustness, interpretability, and multilingual robustness. It is shown that Transformer models offer a robust, scalable platform for future phishing detection systems.

The impact of mental health on employees’ job performance in the hospitality sector

Mathapelo Mabela — 2026-02-09

A lot of attention has been directed at employee mental health lately and this has largely coincided with the increased in prevalence of mental health problems. Mental health has also been highly relevant in the workplace with the hotel sector in South Africa not being spared the challenge. The effects of the pandemic aggravated the matter as it affects the job performance of the employees. Consequently, this study examined the impact of mental health on employee job performance with focus on the hospitality industry in South Africa. Quantitative research approach and a questionnaire was used to collect data. Simple random sampling technique was utilized to collect data from 44 employees of a Hotel in Gauteng province and the data collected was analysed using SPSS. Result from the descriptive statistics revealed that anxiety has an impact on the employees’ as they find themselves in situations where they were anxious only to be relieved when everything is over. Additionally, stress was identified as the factor that influence the mental health of the employees’ job performance, as a result, counselling services are provided by the Hotel. Based on the result of this study, changes can be made regarding promoting awareness and destigmatizing of mental health in workplace. The study recommended that mental health should be promoted in the workplace, flexible schedules should be offered at workplace, workplace stress should be addressed frequently, voluntary benefits should be offered at workplace and lastly, that managers should be trained on mental health management.

Factors affecting the effective implementation of staff performance appraisal system

Tsika Mamosa Eunice — 2026-02-11

The aim of this study is to evaluate the effective implementation of staff performance appraisal system at a government entity. Staff performance appraisal systems are methods and processes used by organizations to assess the level of performance of staff and to provide them with feedback. It is essential for organizations to take measures to ensure that their staff are continuously at their peak performance. The staff performance appraisal system used within the entity fails to enforce a culture that fosters and encourages productivity via motivation, hence the need to evaluate the factors affecting the effective implementation of staff performance appraisal system. The study employed quantitative research approach using random sampling to select 50 employees as participants. Data collected was analysed using SPSS and descriptive statistical to present the data. Findings from the study identified communication, leadership and late performance feedback as the factors affecting the effective implementation of staff performance appraisal system. Lack of trust and attitude of manager was also identified as the reasons for the ineffective implementation of staff performance appraisal system. It is therefore recommended that staff should be trained on the values and mission of the organization, as well as its effect on their job performances. Performance feedback should be effective and timely to assist staff improve on their job performances. Managers should be adequately trained to avoid bias and strive to earn the trust of the staff for the effective implementation of staff performance appraisal system.