The Philippines' Biofuels Act of 2006 has mandated a progressive increase of biofuel blend in the country's fuel mix. This has become one of the country's initiatives on reducing fossil fuel consumption and carbon dioxide emission. This Act has led to the primary utilization of coconut oil for biodiesel production. In the recent years, the frequency of typhoons and insect infestation has led to decrease of biodiesel yield. A shift in the feedstock may help curb this issue, such in the case of algal biofuels. Its high oil yield per hectare and fast growth rate makes algal biofuels ideal for the typhoon-prone archipelagic country. Introducing this new technology to the country would entail detailed assessments on the technology's life cycle. In this regard, the life cycle assessment can be utilized to determine the environmental implications of producing algal-based biofuels in the Philippines. It provides the detailed effects of the life cycle to the different environmental impacts. As these different impacts are multidimensional in nature, weighting prioritization is generally applied as a tool for quantitatively comparing the different impacts. Weight prioritization can be assessed through different multitudes of methodologies where analytic hierarchy process (AHP) is one of the promising approaches. The AHP derives the weight prioritization by acquiring raw data from surveys of a group of stakeholders. A problem arise in the AHP methodology as there can exist inconsistencies and incomplete information from the surveys acquired. Through the use of pattern recognition of the artificial neural network (ANN) algorithm, a probable methodology may be generated to address the inconsistency of the results of the AHP survey. In this paper, we propose the demonstration of the ANN algorithm in creating a model that will fit the data from the survey with the values of the weight prioritization. The study has showed, with 11 hidden nodes, a regression value of 0.96 can be achieved with the predicted weights of the ANN compared to the AHP. The study can be further improved by providing larger quantities of data to the ANN for better training, of which, statistical tools may be applied for generating such data The result of this study can aid in the development of a robust AHP-based decision system for inconsistent and incomplete data.