Estimates of price series for a wide variety of commodities have historically been depended on by investors and governments. This research examines the complex task of projecting scrap steel prices, which are released for the central China market upon a daily basis, using time-series data spanning 08/23/2013–04/15/2021. Prior studies have not adequately considered forecasts for this important commodity price indicator. In this case, cross-validation procedures and Bayesian optimization techniques are used to construct Gaussian process regression strategies, which are then used to provide price projections. With the relative root mean square error being 0.3211%, this empirical prediction framework offers rather precise price projections throughout the out-of-sample time frame extending from 09/17/2019 to 04/15/2021. Using price research models, governments and investors may make educated judgments about local scrap steel markets.