Quantitative investment theory has emerged as a prominent and widely researched domain within the financial markets, where investors predominantly focus on discerning the intricate influences of market dynamics. In this paper, we proposed a short-term prediction-based trading strategy, which can equiponderate between return and risk, considerations while accounting for investor risk preferences. This strategy employs GM(1,1) to capture nuanced features of price dynamics in short-term intervals and update the GM(1,1) model with the latest data. Subsequently, a multi-objective planning equation is formulated to optimize asset allocations by determining the optimal holding that strikes between specific returns and risk mitigation. In the end, this work conducts a case study and sensitivity analysis using five years of gold and bitcoin price data spanning from 2016 to 2021. This empirical examination serves to affirm the efficacy and resilience of the proposed trading strategy. The case study reveals that proficient short-term price forecasting serves as a potent means to proactively mitigate risk, facilitating, judicious and objective trading practices. Moreover, it underscores the strategy’s tangible utility as a guide for real-world investment decisions.