Publicação
Decoding Success with Zero-Inflated and Hurdle Models: Unveiling the Winning Strategies in Portuguese Public Procurement Activity - Evidence from Portugal
| datacite.subject.fos | Ciências Naturais::Ciências da Computação e da Informação | pt_PT |
| dc.contributor.advisor | Damásio, Bruno Miguel Pinto | |
| dc.contributor.advisor | Pinheiro, Flávio Luís Portas | |
| dc.contributor.author | Porto, Leonor Matias | |
| dc.date.accessioned | 2023-11-21T14:37:16Z | |
| dc.date.available | 2023-11-21T14:37:16Z | |
| dc.date.issued | 2023-10-25 | |
| dc.description | Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business Analytics | pt_PT |
| dc.description.abstract | Public procurement plays a vital role in promoting economic development, employment, innovation, and sustainability within the private and public sector. Traditionally, public procurement has been primarily based on lowest-price bids, but recent shifts have emphasized the need for additional evaluation criteria, such as quality, resources capacity, financial stability, experience in the market, innovation, sustainability, and contribution to the society. Therefore, this study aims to predict the success of Portuguese companies in public tender procedures and identify the key factors influencing their success. Additionally, it examines the factors of influence within each contract type to uncover potential variations across different types of contracts. The study makes use of public procurement data from the BASE portal in Portugal, along with business information of the corresponding participants in public procurement, obtained from the global database ORBIS. The combination of these two datasets forms the comprehensive dataset used for analysis in this study. To measure companies’ success in these procedures, the number of public tenders won by each company per year is predicted using count data regression methodologies, considering the discrete nature of the response variable. Advanced models, such as Zero-Inflated and Hurdle models, are employed to effectively handle excess zero values and improve prediction accuracy. The model’s evaluation indicates that these models outperform traditional models in addressing the overdispersion and high variance observed in the data. The results allow to identify and quantify the key factors that significantly influence the success of companies in the public tender procedure within each contract type. Overall, it shows that companies’ size and experience in the public tender’s activity are one of the key factors in the success of winning public tenders. Moreover, the results also shown that the relevance and impact of the different factors studied, which also includes, resources capacity, market experience, profitability and financial stability can vary across contract types. This comprehensive understanding of the determinants of success in public tenders provides valuable insights for companies, enabling them to tailor their strategies and improve their competitiveness in the market. These insights also provide benefits for public authorities by helping to elaborate more effectively the public procurement award criteria and develop targeted policies that support the growth and sustainability of companies facing challenges in the market. These efforts foster a competitive market environment that encourages innovation, economic development, and fair distribution of opportunities. | pt_PT |
| dc.identifier.tid | 203390466 | pt_PT |
| dc.identifier.uri | http://hdl.handle.net/10362/160220 | |
| dc.language.iso | eng | pt_PT |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | pt_PT |
| dc.subject | Public Procurement | pt_PT |
| dc.subject | Count Data Regression | pt_PT |
| dc.subject | Zero-Inflated models | pt_PT |
| dc.subject | Hurdle models | pt_PT |
| dc.subject | SDG 8 - Decent work and economic growth | pt_PT |
| dc.title | Decoding Success with Zero-Inflated and Hurdle Models: Unveiling the Winning Strategies in Portuguese Public Procurement Activity - Evidence from Portugal | pt_PT |
| dc.type | master thesis | |
| dspace.entity.type | Publication | |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | masterThesis | pt_PT |
| thesis.degree.name | Mestrado em Ciência de Dados e Métodos Analíticos Avançados, especialização em Métodos Analíticos para a Gestão | pt_PT |