Variability in the subfertile patient population excludes the possibility of a single approach to controlled ovarian stimulation (COS) covering all the requirements of a patient. Modern technology has led to the development of new drugs, treatment options and quantitative methods that can identify single patient characteristics. These could potentially be used to match patients with the right treatment options to optimise efficacy, safety and tolerability during COS. Currently, age and follicle-stimulating hormone (FSH) level remain the most commonly used single patient characteristics in clinical practice. These variables only provide a basic prognosis for success and indications for standard COS treatment based on gross patient categorisation. In contrast, the anti-Müllerian hormone level appears to be an accurate predictor of ovarian reserve and response to COS, and could be used successfully to guide COS. The antral follicle count is a functional biomarker that could be useful in determining the dose of FSH necessary during stimulation and the success of treatment. Finally, in the future, genetic screening may allow an individual patient's response to stimulation during COS to be predicted based on genotype. Unfortunately, despite the predictive power of these measures, no single biomarker can stand alone as a guide to determine the best treatment option. In the future, hormonal, functional and genetic biomarkers will be used together to personalise COS.