Recent Publications
Collusion risk in corporate networks
Villamil, I., Kertész J. & Fazekas, M.
Collusion among economic operators increases prices, reduces product quality, and hinders innovation. Structural links can affect the incentive and ability of firms to behave competitively by facilitating collusion. We use a network-based approach to study the relationship between ownership links and bidding behavior in procurement markets. We build temporal multiplex networks based on firms’ ownership and co-bidding ties to find network measures that may signal collusion risk. We test four network measures, two at market-level (density and average harmonic closeness centrality) and two at firm-level (degree centrality and harmonic closeness centrality).
Using data on public procurement contracts awarded in Sweden from 2010 to 2015, we found higher incidence of single bidding in markets that are more closely related through ownership links. Missing bidders are also more likely in these markets. Single bidding and missing bidders may indicate the presence of collusive arrangements such as of bid suppression or rotation. For the firm-level analyses, our results showed a positive relationship between winning probability and centrality in the ownership network. A similar result was obtained for cut-point position, indicating that firms that are more closely connected to other firms through ownership links have a more important position in the co-bidding network and are also more likely to win contracts.
Predicting pharmaceutical prices. Advances based on purchase-level data and machine learning
Fazekas, M., Veljanov, Z. & de Oliveira, A.B.
Increased costs in the health sector have put considerable strain on the public budgets allocated to pharmaceutical purchases. Faced with such pressures amplified by financial crises and pandemics, national purchasing
authorities are presented with a puzzle: how to procure pharmaceuticals of the highest quality for the lowest price. The literature explored a range of impactful factors using data on producer and reference prices, but largely
foregone the use of data on individual purchases by diverse public buyers.
Leveraging the availability of open data in public procurement from official government portals, the article examines the relationship between unit prices and a host of predictors that account for policies that can be amended
nationally or locally. The study uses traditional linear regression (OLS) and a machine learning model, random forest, to identify the best models for predicting pharmaceutical unit prices. To explore the association between a wide variety of predictors and unit prices, the study relies on more than 200,000 purchases in more than 800 standardized pharmaceutical product categories from 10 countries and territories.
The results show significant price variation of standardized products between and within countries. Although both models present substantial potential for predicting unit prices, the random forest model, which
can incorporate non-linear relationships, leads to higher explained variance (
R2 = 0.85) and lower prediction error (RMSE = 0.81).
The results demonstrate the potential of i) tapping into large quantities of purchase-level data in the health care sector and ii) using machine learning models for explaining and predicting pharmaceutical prices.
The explanatory models identify data-driven policy interventions for decision-makers seeking to improve value for money.
Skill mismatch and the costs of job displacement
Neffke, F., Nedelkoska, L. & Wiederhold, S.
Establishment closures have lasting negative consequences for the workers displaced from their jobs. We study how these consequences vary with the amount of skill mismatch that workers experience after job displacement. Developing new measures of occupational skill redundancy and skill shortage, we analyze the work histories of individuals in Germany between 1975 and 2010. We estimate difference-in-differences models, using a sample of displaced workers who are matched to statistically similar non-displaced workers.
We find that displacements increase the probability of occupation change eleven-fold. Moreover, the magnitude of post-displacement earnings losses strongly depends on the type of skill mismatch that workers experience in such job switches. Whereas skill shortages are associated with relatively quick returns to the earnings trajectories that displaced workers would have experienced absent displacement, skill redundancy sets displaced workers on paths with permanently lower earnings. We show that these differences can be attributed to differences in mismatch after displacement, and not to intrinsic differences between workers making different post-displacement career choices.
Evaluating the principle of relatedness: Estimation, drivers and implications for policy
Li, Y. & Neffke, F.
A growing body of research documents that the size and growth of an industry in a place depends on how much related activity is found there. This fact is commonly referred to as the “principle of relatedness”. However, there is no consensus on why we observe the principle of relatedness, how best to determine which industries are related or how this empirical regularity can help inform local industrial policy. We perform a structured search over tens of thousands of specifications to identify robust – in terms of out-of-sample predictions – ways to determine how well industries fit the local economies of US cities. To do so, we use data that allow us to derive relatedness from observing which industries co-occur in the portfolios of establishments, firms, cities and countries. Different portfolios yield different relatedness matrices, each of which help predict the size and growth of local industries. However, our specification search not only identifies ways to improve the performance of such predictions, but also reveals new facts about the principle of relatedness and important trade-offs between predictive performance and interpretability of relatedness patterns. We use these insights to deepen our theoretical understanding of what underlies path-dependent development in cities and expand existing policy frameworks that rely on inter-industry relatedness analysis.