Indoor farming is a good alternative farming technique especially in urban areas which lacks an arable land and space for growing crops. Since indoor farming uses artificial environment, it faces many difficulties such as getting the right amount of water, light, temperature, and humidity that are required by crops. These factors highly affect the proper growth and development of crops, its quality, and the output yield. There are existing indoor vertical farming facilities that can mimic the natural environment but don’t address the efficiency and cost of the overall system. In this study, an existing indoor vertical farming was modified by designing a low-cost smart monitoring and control system that uses machine learning technique to autonomously control the actuators such as the cooling fans, water valve, and LED lights based on the following descriptors: temperature, humidity, soil moisture level, and the health status of the Lactuca sativa L. or commonly known as lettuce. The modified system achieved a better growth compared to the traditional method. The height, length and width of the lettuce is found to be better by 20 % and the color of the system’s output is greener than the usual. The cost incurred is 54 % and 19 % cheaper with regards to the energy consumption and the water consumption.