Supplier selection with multi-scenario inputs and outputs, using data envelopment analysis

Data Envelopment Analysis (DEA) is a powerful tool for assessing the relative efficiency of Decision-Making Units (DMUs) by comparing their input-output ratios. Traditional DEA models typically address crisp data but may not fully capture scenarios involving uncertainty in inputs and outputs. This research expands on DEA by applying it to multiple scenarios to account for varying conditions in farms across Canada. This research applies DEA to assess the operational efficiency of greenhouse, sod, and nursery operations across Canada, using a multi-scenario approach over the period from 2019 to 2023. The study focuses on three key provinces, British Columbia, Ontario, and Quebec, making the sample size as 3, examining their performance based on various input variables, such as operating expenses for specialized greenhouse vegetables and flowers, and output variables, including the total value of greenhouse products produced. This model, derived from traditional DEA formulations but adapted for multiple scenarios, remains linear and computationally efficient, overcoming common limitations of non-linear models. Results indicate that Quebec consistently achieved full efficiency, while Ontario and British Columbia improved over time but did not reach Quebec's level. This study introduces a new application of DEA with the incorporation of a multi-scenario approach in order to capture the variation and uncertainty within the greenhouse, sod, and nursery operations in Canada which will improve the quality and strength of efficiency analyses relevant to agricultural settings. Despite its advancements, the study acknowledges limitations, including static analysis, homogeneity assumptions, and the exclusion of qualitative factors.