The AI can revolutionize the electrospinning process by significantly reducing costs and improving efficiency through real-time parameter optimization. However, creating AI models requires large amounts of quality data, the acquisition of which can be expensive and time-consuming. In the specific case of nanofiber production, obtaining comprehensive datasets involves numerous laboratory experiments. Due to the fundamental importance of data in AI, the presence of missing data can lead to several problems, such as the introduction of bias and difficulty in detecting significant relationships. So, this research work article discusses the cost-benefit analysis of different imputation methods for datasets. The study presented compares the impact of three imputation methods. Imputation using artificial neural networks stands out as a promising technique for these types of data sets with a significant number of missing values. However, when deciding which imputation method to choose, there must be a balance between the acceptable error rate and the amount of effort one is willing to expend to reduce that error.