In recent years, e-commerce has been established as one of the dominant ways of making commercial transactions. Efficient pricing policy strategies employed by businesses are critical for their survival in highly competitive markets, in order to achieve their goals and maximise their profits. Various dynamic pricing algorithms have been implemented and adapted to the continuously changing conditions of the online markets. These algorithms benefit from the abundance of data available to the online stores, data related to market conditions as well as customers' preferences and consumption habits. Utilizing the above data and integrating them into dynamic pricing strategies can give a significant competitive advantage to businesses. However, so far these techniques have been applied to limited business domains, e.g. airline and hotel bookings. This diploma thesis focuses on the development of dynamic pricing methods for online stores that take into account demand, competition, available stock, as well as user profiles. The system created combines the mentioned data and uses neural networks in conjunction with optimization and personalization methods and algorithms in order to set dynamically the price for each product per customer in order to optimise the conversion rate.