Trend-Adjusted Time Series Models with an Application to Gold Price Forecasting
This work addresses forecasting challenges in volatile financial time series, such as gold prices, by introducing a trend-adjusted approach, though it appears incremental as it builds on existing LSTM methods with a novel adjustment.
The paper tackles time series forecasting by reframing it as a two-part task involving trend prediction and quantitative value forecasting, proposing the Trend-Adjusted Time Series (TATS) model that adjusts forecasts based on predicted trends, and demonstrates that TATS outperforms standard LSTM and Bi-LSTM models with significantly lower forecasting error on daily gold price data.
Time series data play a critical role in various fields, including finance, healthcare, marketing, and engineering. A wide range of techniques (from classical statistical models to neural network-based approaches such as Long Short-Term Memory (LSTM)) have been employed to address time series forecasting challenges. In this paper, we reframe time series forecasting as a two-part task: (1) predicting the trend (directional movement) of the time series at the next time step, and (2) forecasting the quantitative value at the next time step. The trend can be predicted using a binary classifier, while quantitative values can be forecasted using models such as LSTM and Bidirectional Long Short-Term Memory (Bi-LSTM). Building on this reframing, we propose the Trend-Adjusted Time Series (TATS) model, which adjusts the forecasted values based on the predicted trend provided by the binary classifier. We validate the proposed approach through both theoretical analysis and empirical evaluation. The TATS model is applied to a volatile financial time series (the daily gold price) with the objective of forecasting the next days price. Experimental results demonstrate that TATS consistently outperforms standard LSTM and Bi-LSTM models by achieving significantly lower forecasting error. In addition, our results indicate that commonly used metrics such as MSE and MAE are insufficient for fully assessing time series model performance. Therefore, we also incorporate trend detection accuracy, which measures how effectively a model captures trends in a time series.