This study presents a comparative approach to short-term forecasting of five technology-focused exchange-traded funds (ETFs)—AIQ, BOTZ, QQQ, VGT, and XLK—using two modelling techniques: the Auto-Regressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) neural networks. Each ETF’s daily closing prices were first analysed through descriptive statistics. Then, both models were trained to forecast the subsequent five trading days. Performance was evaluated using Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). Experimental results show that LSTM achieved lower MAPE across all ETFs, averaging 4.5%, compared to ARIMA’s 5.5%. While LSTM captured trends and volatility more effectively, ARIMA performed relatively well under stable conditions but failed to react to abrupt shifts. Visual comparisons of historical trends and forecasts are provided, along with practical insights for finance researchers and investors. The study concludes with a discussion of model limitations and proposes directions for integrating hybrid forecasting approaches.