In this study, the efficacy of 21 distinct surface post-processing methods on the fatigue behavior of an additively manufactured (AM) material was investigated. Various treatments, encompassing single-step processes like sand blasting (SB), conventional shot peening (CSP), severe shot peening (SSP), gradient severe shot peening (GSSP), ultrasonic shot peening (USP), severe vibratory peening (SVP), ultrasonic nanocrystal surface modification (UNSM), laser shock peening (LSP), laser polishing (LP), tumble finishing (TF), chemical polishing (CP), electro-chemical polishing (ECP), and machining (M), as well as hybrid treatments, were systematically investigated for their impact on the fatigue behavior of hourglass laser powder based fused (LB-PBF) AlSi10Mg specimens. A comprehensive series of experimental tests were carried out, covering surface texture analyses, microstructural characterizations, porosity measurements, hardness, residual stresses (RS), monotonic tensile tests, and rotating bending fatigue tests at four stress levels. Following the experimental investigations, the acquired data were leveraged to develop a machine learning (ML)-based model to correlate the fatigue life with the influencing factors and conduct parametric and sensitivity analyses. The model utilized a deep learning approach to predict the fatigue response of LB-PBF AlSi10Mg, incorporating various artificial neural networks (ANNs) and considering input parameters such as yield strength, ultimate tensile strength, elongation to fracture, porosity, depth of pore closure, surface hardness, depth of hardness variation, surface RS, maximum compressive residual stresses (CRS), depth of the CRS field, top surface grain size, surface layer mean grain size, surface roughness, and stress amplitude. Depending on the life regime, the factors influencing fatigue behavior can vary significantly. In higher stresses, dominated by plastic strains, surface residual stress emerges as the primary factor. Conversely, in lower stresses, dominated by elastic strains, the significance of surface roughness becomes more pronounced, followed by surface residual stress, surface hardness and other factors. These findings underscore the contextual importance of different influencing factors for enhancing fatigue resistance based on varying loading conditions.