In the construction industry, estimating the realistic lifespan of buildings is essential to properly perform life cycle assessments (LCAs). It is impractical to consider all of the different factors affecting building lifespan; therefore, most LCAs assume a standard building lifespan for each major type of building structure. However, the lifespans of buildings vary significantly in practice, and applying a uniform lifespan to all buildings with the same structural type may lead to completely erroneous LCA results. In this study, LCAs of waterproofing methods on building models and actual buildings in Korea are used to empirically demonstrate the effect of realistic lifespan prediction using big data. Applying a more representative building lifespan of 5–39 years in the waterproofing LCAs of an architectural model decreased the carbon emissions in all phases (construction, operation and maintenance, and demolition) by 78–24%, respectively, relative to a 50-year lifespan assumption. During the maintenance phase, the reductions were 100–31%, respectively. The accuracy of the waterproofing LCAs of 17 real buildings became more irregular as the percentage error of the predicted lifespan increased, although the LCA analysis results had 0% error for buildings with a predicted lifespan error of 6% or less. Therefore, depending on the research purpose, a low-error predictive building lifespan model can evidently support accurate LCA results. This study proves that the use of a big data-based building lifespan prediction method is essential for LCA and is an effective tool for business planning and critical decision-making throughout the construction process.