Time Series Analysis and Forecasting

This study was carried out to evaluate trypanocides by cattle farmers in Ogun State, Nigeria. A total of 143 respondents were sampled from 13 cattle markets in Yewa, Egba and Ijebu zones using a stratified proportionate random sampli revealed that majority (40%) were between 21 and 40 years of age which indicated that cattle production is an adult dominated activity. Majority of the respondents practiced Islam with about 21 to 40years of experience in cattle production. However, it was recorded that most (80%, 90.9% and 94%) of the respondents in the zones have the knowledge about trypanosomosis. Whilst majority of the respondents believed that fly bites and seasons are the major causes of trypanosomosis. The sign that projects the occurrence of infection were mainly loss appetite (27.3% in Egba, 30% in Ijebu and 24% in Yewa) and loss of weight (28% in Yewa, 23.6% in Egba and 27.5% in Ijebu) respectively.Moreover, majority (64% in Yewa, 63.6% in Egba and 62.5% in practiced self-medication in tackling the occurrence of trypanosomosis while consulting Veterinarians in the management of trypanosomosis is poor (8% in Yewa, 10.9% in Egba and 12.5% in Ijebu). It is concluded that high usage of trypanocidesmay result to high prevalence of drug residues in the edible animal organs and milk obtained from animals in the three geopolitical zones of Ogun State. It is however recommended that effective control of trypanosomosis in cattle or livestock generally is dependent on the appropriate chemotherapeutic strategies designed to combat the infection. This requiresregular inspection and administration of drugs should be strictly handled by Veterinary experts in the field.

Primary capital market i.e. Initial Public Offering (IPO) market forms a significant part of it. India, an emerging market, has seen tremendous growth in the BSE SME IPO market over the past few years. There are times when India experiences a high volume of BSE SME IPOs. On the other hand, there have been times when there haven't been many BSE SME IPOs. Investing in the Share market is been a trendsetter for most of investors. The Present study clarifies the major influence of S&P BSE SME IPO in India. The Study will discuss Risk and Return which help to reduce the risk for investors. Based on the S&P BSE SME IPO the study found that high return is achieved in the recent years of the study period. So, investors can invest their money in the SME IPO to gain profit in the Future and there is an increase level of SME IPO in and after COVID-19, it means after 2019 there is high investors in BSE SME IPO. So, the investor should aware about the market condition before investing. The Present Study Provides a detailed analysis about Risk and Return of S&P BSE SME IPO in India and trend and growth of BSE SME IPO for January 2013 to December 2022 by taking monthly and yearly observation. It is Observed that the risk and return for the above-investigated S&P BSE SME IPO at a moderate level.

The exponential growth of urbanization has intensified environmental degradation, particularly in terms of air pollution, posing severe health and ecological risks to urban populations. Traditional air quality monitoring systems, while effective in data collection, often fall short in predictive capability and real-time responsiveness. In this context, artificial intelligence (AI)-driven predictive modeling emerges as a transformative tool in environmental risk assessment, offering advanced analytical techniques that can not only evaluate current air quality conditions but also forecast future pollution levels with remarkable accuracy. This study proposes a comprehensive AI-based framework for predictive modeling aimed at assessing air quality and anticipating environmental risks in urban ecosystems. The proposed model integrates multiple data streams-including meteorological parameters, vehicular emissions, industrial discharge data, and real-time pollutant concentrations (e.g., PM2.5, NO₂, CO, O₃)-using machine learning algorithms such as Long Short-Term Memory (LSTM) networks, Random Forests, and Gradient Boosting Machines. The methodology emphasizes data preprocessing techniques, including normalization, missing value imputation, and outlier detection, to enhance model reliability. The spatial-temporal analysis is conducted to identify pollution hotspots and patterns across different urban zones. A novel feature of this study is the implementation of ensemble modeling, which combines the strengths of various AI algorithms to improve predictive accuracy and minimize error margins. The model was trained and validated using historical air quality datasets from metropolitan regions across different climatic zones. Results indicate a significant improvement in predictive performance when compared to traditional statistical models, with forecasting accuracy exceeding 90% in several cases. Moreover, the system demonstrates the capacity to issue early warnings related to critical pollution thresholds, enabling proactive interventions by urban planners and public health authorities. Beyond prediction, the model offers risk classification and prioritization by estimating the probable health impact indices based on demographic vulnerability and pollutant toxicity. The interpretability of model outputs is enhanced using SHAP (Shapley Additive exPlanations) values to ensure transparency and stakeholder trust. Furthermore, a user-friendly dashboard was developed to present real-time visualizations and alerts for municipal decision-makers. In conclusion, this research underscores the transformative role of AI in environmental governance, illustrating how predictive modeling can elevate urban sustainability by fostering data-driven policy-making. The proposed AI framework holds vast potential for scalability and adaptation across global urban centers striving for resilience against the escalating challenge of air pollution.

Abstract: In many developing countries, poor management of perishable goods causes significant economic and nutritional
losses. For example, food waste rates in sub-Saharan Africa are over 50%. Most smart inventory systems are designed for
large companies with plenty of data and strong infrastructure, so small and medium-sized businesses (SMEs) often have
limited options. This study introduces a machine learning-based software framework for smarter inventory monitoring and
demand forecasting of perishable goods, tailored for retail SMEs with limited resources. The framework was tested using
real-world data from Sierra Leone. Five forecasting models were compared: Linear Regression (as a baseline), Random
Forest (ultra-tuned), XGBoost (ultra-optimised), a Stacking Ensemble, and a Hybrid XGBoost-LSTM model. Tests on a
combined dataset, using both a UCI retail transaction set and a synthetic Sierra Leone dataset, showed that the XGBoost
UltraOptimised model had the best accuracy (R2 = 0.9781, MAE = 81.99 units), cutting forecasting errors by 89% compared
to the linear baseline (MAE = 741.07). Analysis showed that short-term demand momentum variables were the most
important, making up over 87% of the model’s predictive power. The framework combines predictive modelling with a
modular decision-support system that gives reorder alerts, wastage warnings, and inventory trend forecasts. It can run on
standard computers without needing high-speed internet, making it practical for SMEs. The results show that welladapted
machine learning tools can help close the gap between advanced algorithms and real-world needs in developing countries,
helping reduce food waste, improve supply chains, and support SME growth.

This paper predicts Coronavirus Disease (COVID-19)'s potential influence on the Arab country's economy by using two predicting models: the Autoregressive Integrated Moving Average (ARIMA) model and Long Short-Term Memory (LSTM) model. The World Bank offers data of the Arab countries' Gross Domestic Product (GDP) over the period 1968-2019. As we show up at the pinnacle of the COVID-19 pandemic, quite possibly the most critical inquiry going up against us is: what is the potential impact of the pandemic on the rate of GDP in Arab countries during the pandemic period? LSTM is recurrent neural networks (RNN), which are competent in understanding temporal dependencies. Therefore, the model based on LSTM achieved a great fit with the real data, which is what made us rely on its results more than the ARIMA model. The results of the LSTM model showed that the COVID-19 pandemic caused a decrease in GDP by approximately 17.22% and 5.41% in 2020 and 2021, respectively, with respect to the real GDP announced by the World Bank. In addition, we trained the LSTM-based model on real data from 1968 to 2020 and predicted the GDP growth rate in the next five years until 2025. Thus, what is certain now is that the Arab world states have to encounter the challenges presented by the current ecosystem. Transition to digital economy is needed, additional volume of data with high-level accuracy is required to improve precise and robust models to attain projections with a reduced amount of margin of error.

Livebirths and stillbirths are key public health indicators, with significant social and economic consequences. This study employs time series modeling to analyze quarterly records of livebirths and stillbirths obtained fom Obafemi Awolowo University Teaching Hospitals Complex (OAUTHC), Ile-Ife, Nigeria, covering the period from 2001 to 2020. The Augmented Dickey Fuller test confirmed the stationarity of the series, after which the Autocorrelation (ACF) and Partial Autocorrelation (PACF) functions were examined, identify suitable ARMA models. Model selection was guided by the Akaike Information criteria (AIC), Bayesian Information Criterion (BIC), and Hannan Quinn Criterion (HQIC). The models with the lowest information criteria ARMA (2,3) for livebirths and ARMA(1,3) for stillbirths were selected as optimal. Diagnostic checks revealed no significant autocorrelation in the residuals with ACF and PACF plots showing values close to zero across lags, confirming model adequacy and reliability. Forecast results indicate that livebirths will experience short term fluctuations before reaching a stable trend while stillbirth are projected to remain relatively constant at approximately 30 cases per quarter, though with broader confidence intervals at the start of the forest. The relatively low R2 values, particularly for stillbirths suggest that other unobserved variables such as healthcare accessibility, maternal risk factors and socioeconomic conditions may also influence outcomes. Overall, the study emphasizes the importance of continuous improvements in maternal and child healthcare as well as the value of data driven decision making for public health planning and intervention.

Livebirths and stillbirths are key public health indicators, with significant social and economic consequences. This study employs time series modeling to analyze quarterly records of livebirths and stillbirths obtained fom Obafemi Awolowo University Teaching Hospitals Complex (OAUTHC), Ile-Ife, Nigeria, covering the period from 2001 to 2020. The Augmented Dickey Fuller test confirmed the stationarity of the series, after which the Autocorrelation (ACF) and Partial Autocorrelation (PACF) functions were examined, identify suitable ARMA models. Model selection was guided by the Akaike Information criteria (AIC), Bayesian Information Criterion (BIC), and Hannan Quinn Criterion (HQIC). The models with the lowest information criteria ARMA (2,3) for livebirths and ARMA(1,3) for stillbirths were selected as optimal. Diagnostic checks revealed no significant autocorrelation in the residuals with ACF and PACF plots showing values close to zero across lags, confirming model adequacy and reliability. Forecast results indicate that livebirths will experience short term fluctuations before reaching a stable trend while stillbirth are projected to remain relatively constant at approximately 30 cases per quarter, though with broader confidence intervals at the start of the forest. The relatively low R2 values, particularly for stillbirths suggest that other unobserved variables such as healthcare accessibility, maternal risk factors and socioeconomic conditions may also influence outcomes. Overall, the study emphasizes the importance of continuous improvements in maternal and child healthcare as well as the value of data driven decision making for public health planning and intervention.

Groundwater is the largest liquid freshwater reservoir and a critical resource for drinking water, agriculture, and ecosystem sustainability. In the Rajshahi Division of northwestern Bangladesh, intensive groundwater use and recurring droughts necessitate an accurate assessment of groundwater level (GWL). This study presents an integrated framework combining statistical, machine learning, and spatial tools for a comprehensive assessment of GWL fluctuations. A total of 1008 artificial neural network (ANN) models and 768 autoregressive integrated moving average (ARIMA) models were developed and evaluated under univariate (UV) and multivariate (MV) settings to determine optimal model functions and lagged effects. Spatial GWL and trend variations were generated using ArcGIS. Results show that ANN models incorporating rainfall (RF) data improved predictive accuracy (e.g., Bogura, MSE 0.01, Correlation Coefficient R = 0.98, NSE = 0.97, KGE = 0.96, R 2 = 0.97) compared to UV models. ARIMA models slightly outperformed ANN due to linear patterns, while ANN captured nonlinear dynamics. Trend analysis indicated significant GWL increases at Nawabganj. This framework provides a robust, transferable approach for evaluating GWL, enabling sustainable irrigation planning, drought risk management, identification of vulnerable zones, and evidence-based groundwater management in other hydrologically stressed regions.

This paper provides a comprehensive analysis of current account sustainability in the Democratic Republic of Congo (DRC), focusing on the structural determinants of persistent external imbalances and the policy mechanisms required for sustainable adjustment. Drawing on both theoretical and empirical frameworks, the study demonstrates that the DRC's current account deficit is predominantly structural, rooted in weak economic diversification, chronic service deficits, and significant primary income outflows linked to foreign-owned extractive industries. Using a mixed methodological approach, including descriptive analysis and econometric modeling, the findings reveal that external imbalances are closely tied to domestic structural constraints and limited absorptive capacity. The paper argues that sustainable adjustment requires not only macroeconomic stabilization but also deep structural transformation, including industrial diversification, financial development, and improved allocation of foreign direct investment (FDI). The study contributes to the broader literature on current account sustainability in resource-dependent economies and offers policy recommendations tailored to the Congolese context.

Groundwater is the largest liquid freshwater reservoir and a critical resource for drinking water, agriculture, and ecosystem sustainability. In the Rajshahi Division of north-western Bangladesh, intensive groundwater use and recurring droughts necessitate an accurate assessment of groundwater level (GWL). This study presents an integrated framework combining statistical, machine learning, and spatial tools for a comprehensive assessment of GWL fluctuations. A total of 1008 artificial neural network (ANN) models and 768 autoregressive integrated moving average (ARIMA) models were developed and evaluated under univariate (UV) and multivariate (MV) settings to determine optimal model functions and lagged effects. Spatial GWL and trend variations were generated using ArcGIS. Results show that ANN models incorporating rainfall (RF) data improved predictive accuracy (e.g., Bogura, MSE 0.01, Correlation Coefficient R = 0.98, NSE = 0.97, KGE = 0.96, R 2 = 0.97) compared to UV models. ARIMA models slightly outperformed ANN due to linear patterns, while ANN captured nonlinear dynamics. Trend analysis indicated significant GWL increases at Nawabganj. This framework provides a robust, transferable approach for evaluating GWL, enabling sustainable irrigation planning, drought risk management, identification of vulnerable zones, and evidence-based groundwater management in other hydrologically stressed regions.

Rice is the main staple food for the majority of the Indonesian population. However, the fluctuation in rice prices and future uncertainty emphasize the importance of forecasting rice prices, thus requiring a forecasting model capable of providing accurate predictions. Various previous forecasting methods have been limited in capturing the combination of linear and non-linear patterns in rice price data, spurring the need for a more comprehensive hybrid approach. This research applies a quantitative approach by utilizing secondary data sourced from publications of the Central Statistics Agency (BPS) of Indonesia. This study aims to forecast rice prices in Indonesia using a hybrid approach combining Holt–Winters Exponential Smoothing (HWES) with Multilayer Perceptron (MLP). The hybrid model is designed to overcome the limitations of the Holt-Winters Exponential Smoothing method, which can only capture linear patterns such as trend and seasonality, by adding the Multilayer Perceptron method to capture non-linear patterns that cannot be handled by the linear approach. The dataset comprises monthly rice prices in Indonesia from January 2010 to December 2024, while the period of January–December 2025 is used as the prediction period. The data analysis process was carried out using the software R-Studio and Minitab, which provide a variety of features to support time series modeling. The results indicate that the most effective method for forecasting rice prices in Indonesia is the Hybrid Holt Winters Exponential Smoothing (α = 0.5; β = 0.3; γ = 0.3)-Multilayer Perceptron (12-12-1), which achieved the highest accuracy with a MSE of 9666.12, a RMSE of 310.9117, and a MAPE of 1.9949%. This finding indicates that the Hybrid HWES-MLP approach is highly capable of capturing rice price data patterns. Thus, this model holds significant potential to be utilized as a benchmark supporting government policy in maintaining rice price stability, market intervention, and optimizing the management of national rice reserves stock.