Hydraulic fracturing operations affect reservoir flow dynamics and increase production in unconventional tight reservoirs. The control of fracture growth and geometry presents challenges in formations in which the boundary lithologies are not highly stressed in comparison to the pay zone, thus failing to prevent the upward migration of fractures. Several factors influence the growth and geometry of fractures, including reservoir, wellbore, and fluid/proppant parameters. Successful results require a thorough knowledge of reservoir parameters, including stress distribution and the appropriate use of corresponding wellbore components and fluid/proppant. The success of a hydraulic fracturing treatment is highly correlated with control of the created fracture geometry.This paper discusses a study in which a numerical fracture model is used to design the fractures in a tight oil reservoir. Fracture treatment designs include the selection of fracturing fluids, additives, proppant materials, injection rate, pumping schedule, and fracture dimensions. Using the fracture model, a statistically representative synthetic set of data is generated for each parameter to build data-driven models.The performance of the data-driven models is validated by comparing the results to a numerical model, and considering the significance of parameters, including size, number, location, phasing angle of perforations, fluid and proppant type, rock strength, porosity, and permeability on the fracture design optimization using various fracture models. Data-driven predictive models are generated by using neural networks (NN) and support vector machine (SVM) algorithms. Optimum values of model parameters are also investigated.The SVM and NN models are used to optimize the fracturing treatments per well, and are evaluated based on accuracy and computational complexity. Based on the performances of the models, model parameters are adjusted to obtain fit-for-purpose well-based hydraulic fracturing models.