With the growth of the technology-driven world, today many designs and analyzes depend on smart software to address different computational concepts. In the meantime, locating and finding a suitable place for establishing a facility is one of them and is considered by urban designers, regional planners, and architects. Accordingly, the main goal of this study is developing a plugin in QGIS to aid in the decision-making of selecting the location of a new manufacturing plant by prioritizing the places that have the most renewable energies. Considering this logic has two main purposes; the first one is renewable resources, such as sunlight, wind, rain, tides, waves, and geothermal heat can supply all the energies needed for the productions of these factories while causing as little harm to the environment as possible. Second, we can locate these factories in locations with a low unemployment rate while providing maximum suitable conditions and facilities for the workers, thus helping to reduce unemployment rates in those areas. To reach these main goals, we developed a computational system titled the site selection decision making (SSDM | Site Selection Decision Making) plugin in QGIS3.12 software. The clustering method was used for clustering the important locations based on their accessibility to other facilities. Then binary classification which is a supervised machine learning algorithm, and its goal is to predict categorical class labels including discrete and unordered format was used for analysis and returning the final results. Pycaret library; pycaret.classification has been used for implementing the machine learning algorithm. In this regard, binary classification determines whether a site is suitable for establishing a new industrial factory or not. Therefore, its answer is yes or no considering several significant factors.