We investigated a suite of impact glass‐bearing rocks using a multi‐analytical approach including visible‐near‐infrared diffuse reflectance spectroscopy, Mössbauer spectroscopy, and powder X‐ray diffraction. In order to better understand and interpret the obtained results, we built a database containing physical, chemical, and spectroscopic information on glasses and glass‐bearing materials using new results from this study and published works. We used the database to explore systematic relationships between parameters of interest and finally we applied several machine learning algorithms (support vector machine, random forests, and gradient boosting) to test the possibility to regress the oxidation state of iron from chemical and spectroscopic information. Our results show that even small amounts of mafic crystalline phases have a big influence on the spectral features of glass‐bearing rocks. Samples without mafic crystalline inclusions show the typical spectrum of glasses (two broad and shallow bands roughly centered around 1,100 and 1,900 nm) with minor variations due to bulk chemistry. We described a non‐linear relationship between average reflectance (average reflectance value between 500 and 1,000 nm), FeO + TiO2 content, grain size, and Fe3+/FeTOT. We tested the relation for the finer grain size (0–25 μm), and we qualitatively assessed how it is affected by grain size, Fe3+/FeTOT, and crystal content. Finally, we developed a machine learning pipeline to regress the Fe3+/FeTOT of glass‐bearing materials using the proposed database. Our machine learning calculations give satisfactory results (MAE: 0.0321) and additional data will enable the application of our computational strategy to remotely acquired data to extract chemical and mineralogical information of planetary surfaces. Plain Language Summary Glasses and glass‐bearing rocks are abundant on many planetary surfaces. Glass‐bearing rocks form either as a result of rapid cooling of volcanic materials or after shock impact of (large enough) planetary bodies. Their detection from remotely acquired data remains a challenge due to the many variables affecting their spectroscopic features. More data are necessary in order to improve our knowledge of these materials. In this work, we investigated a suite of terrestrial rocks formed after impact/near surface explosion of asteroids. These rocks are characterized by a varied chemistry and different degrees of glass‐crystal ratios, making them very interesting analog planetary materials. We characterized the spectroscopic, chemical, and mineralogical features of these rocks, and we built a database containing similar information retrieved from literature data. The newly compiled database allowed us to uncover relationships between spectroscopic features and chemical/physical features of glass‐bearing materials. Given the extremely complicated physics of the shock phenomena, it is not always easy to extract useful information from the spectra of these materials. For this reason, we applied some machine learning algorithms to the newly compiled database in order to retrieve information of interest. The approach that we use is successful and suggests that when there will be more data in the database, it would be possible to use more sophisticated algorithms to retrieve information of interest from remotely acquired data. Key Points The average reflectance in the visible‐near‐infrared spectral range is negatively correlated with FeO + TiO2 content in glassy materials A database was built merging spectral, chemical, and physical information from several literature data The redox state of iron in glassy materials can be successfully regressed by a machine learning approach using spectroscopic information