Modeling and Forecasting PZ Cussons Nigeria PLC Daily Stock Prices Using SARIMA: An Empirical Analysis

This study conducts a comprehensive empirical analysis of modeling and forecasting the daily stock prices of PZ Cussons Nigeria PLC using the Seasonal Autoregressive Integrated Moving Average (SARIMA) framework within the Box-Jenkins methodology. Utilizing a dataset of 2,289 daily closing prices spanning from January 5, 2015, to November 22, 2023, the research rigorously compares the forecasting performance of SARIMA against a non-seasonal ARIMA benchmark. Stationarity is assessed via the Augmented Dickey-Fuller (ADF) test, with model selection guided by the Akaike Information Criterion (AIC). The optimal models identified are SARIMA(1,0,1)(0,3,2,20) and ARIMA(5,3,0), with diagnostic checks confirming adequacy through residual analysis and Ljung-Box tests. Forecast accuracy is evaluated out-of-sample using root mean squared error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE) across multiple horizons. Results indicate that while ARIMA exhibits marginally lower RMSE in short-term forecasts, SARIMA consistently outperforms in MAPE and demonstrates superior robustness over medium to long-term horizons, particularly beyond one month. Trading strategy backtests further reveal that SARIMA-based signals yield significantly higher cumulative returns (15.5% vs. 8.1%), hit rates (56% vs. 47%), and Sharpe ratios (1.12 vs. 0.68), with lower maximum drawdowns. These findings underscore the critical role of seasonality potentially driven by institutional rebalancing, fiscal cycles, and behavioral market responses in Nigerian equity price dynamics. The study contributes to the literature on financial econometrics in emerging African markets by providing empirical evidence that SARIMA offers enhanced predictive accuracy and practical trading utility compared to traditional ARIMA, affirming the relevance of classical time series models in contemporary quantitative finance.