arXiv subjects

Andrea Zaccaria

Publications and source records attributed to Andrea Zaccaria.

At least 37 records · Page 2Linked to original sources

arXiv2021

Which will be your firm's next technology? Comparison between machine learning and network-based algorithms

We reconstruct the innovation dynamics of about two hundred thousand companies by following their patenting activity for about ten years. We define the technological portfolios of these companies as the set of the technological sectors present in the patents they submit. By assuming that companies move more frequently towards related sectors, we leverage on their past activity to build network-based and machine learning algorithms to forecast the future submission of patents in new sectors. We compare different evaluation metrics and prediction methodologies, showing that tree-based machine learning algorithms overperform the standard methods based on networks of co-occurrences. This methodology can be applied by firms and policymakers to disentangle, given the present innovation activity, the feasible technological sectors from those that are out of reach, given their present innovation activity.

physics.soc-ph↗

arXiv2021

Universal Database for Economic Complexity

We present an integrated database suitable for the investigations of the Economic development of countries by using the Economic Fitness and Complexity framework. Firstly, we implement machine learning techniques to reconstruct the database of Trade of Services and we integrate it with the database of the Trade of the physical Goods, generating a complete view of the International Trade and denoted the Universal database. Using this data, we derive a statistically significant network of interaction of the Economic activities, where preferred paths of development and clusters of High-Tech industries naturally emerge. Finally, we compute the Economic Fitness, an algorithmic assessment of the competitiveness of countries, removing the unexpected misbehaviour of Economies under-represented by the sole consideration of the Trade of the physical Goods.

econ.GN↗

arXiv2021

Citations or dollars? Early signals of a firm's research success

Scientific and technological progress is largely driven by firms in many domains, including artificial intelligence and vaccine development. However, we do not know yet whether the success of firms' research activities exhibits dynamic regularities and some degree of predictability. By inspecting the research lifecycles of 7,440 firms, we find that the economic value of a firm's early patents is an accurate predictor of various dimensions of a firm's future research success. At the same time, a smaller set of future top-performers do not generate early patents of high economic value, but they are detectable via the technological value of their early patents. Importantly, the observed predictability cannot be explained by a cumulative advantage mechanism, and the observed heterogeneity of the firms' temporal success patterns markedly differs from patterns previously observed for individuals' research careers. Our results uncover the dynamical regularities of the research success of firms, and they could inform managerial strategies as well as policies to promote entrepreneurship and accelerate human progress.

physics.soc-ph↗

arXiv2021

Product Progression: a machine learning approach to forecasting industrial upgrading

Economic complexity methods, and in particular relatedness measures, lack a systematic evaluation and comparison framework. We argue that out-of-sample forecast exercises should play this role, and we compare various machine learning models to set the prediction benchmark. We find that the key object to forecast is the activation of new products, and that tree-based algorithms clearly overperform both the quite strong auto-correlation benchmark and the other supervised algorithms. Interestingly, we find that the best results are obtained in a cross-validation setting, when data about the predicted country was excluded from the training set. Our approach has direct policy implications, providing a quantitative and scientifically tested measure of the feasibility of introducing a new product in a given country.

cs.LG↗

arXiv2021

AI Specialization for Pathways of Economic Diversification

The growth in AI is rapidly transforming the structure of economic production. However, very little is known about how within-AI specialization may relate to broad-based economic diversification. This paper provides a data-driven framework to integrate the interconnection between AI-based specialization with goods and services export specialization to help design future comparative advantage based on the inherent capabilities of nations. Using detailed data on private investment in AI and export specialization for more than 80 countries, we propose a systematic framework to help identify the connection from AI to goods and service sector specialization. The results are instructive for nations that aim to harness AI specialization to help guide sources of future competitive advantage. The operational framework could help inform the public and private sector to uncover connections with nearby areas of specialization.

cs.CY↗

arXiv2021

Relatedness in the Era of Machine Learning

Relatedness is a quantification of how much two human activities are similar in terms of the inputs and contexts needed for their development. Under the idea that it is easier to move between related activities than towards unrelated ones, empirical approaches to quantify relatedness are currently used as predictive tools to inform policies and development strategies in governments, international organizations, and firms. Here we focus on countries' industries and we show that the standard, widespread approach of estimating Relatedness through the co-location of activities (e.g. Product Space) generates a measure of relatedness that performs worse than trivial auto-correlation prediction strategies. We argue that this is a consequence of the poor signal-to-noise ratio present in international trade data. In this paper we show two main findings. First, we find that a shift from two-products correlations (network-density based) to many-products correlations (decision trees) can dramatically improve the quality of forecasts with a corresponding reduction of the risk of wrong policy choices. Then, we propose a new methodology to empirically estimate Relatedness that we call Continuous Projection Space (CPS). CPS, which can be seen as a general network embedding technique, vastly outperforms all the co-location, network-based approaches, while retaining a similar interpretability in terms of pairwise distances.

physics.soc-ph↗

arXiv2020

Emergence of polarization in a voter model with personalized information

The flourishing of fake news is favored by recommendation algorithms of online social networks which, based on previous users activity, provide content adapted to their preferences and so create filter bubbles. We introduce an analytically tractable voter model with personalized information, in which an external field tends to align the agent opinion with the one she held more frequently in the past. Our model shows a surprisingly rich dynamics despite its simplicity. An analytical mean-field approach, confirmed by numerical simulations, allows us to build a phase diagram and to predict if and how consensus is reached. Remarkably, polarization can be avoided only for weak interaction with the personalized information and if the number of agents is below a threshold. We analytically compute this critical size, which depends on the interaction probability in a strongly non linear way.

physics.soc-ph↗

arXiv2020

Dynamical approach to Zipf's law

The rank-size plots of a large number of different physical and socio-economic systems are usually said to follow Zipf's law, but a unique framework for the comprehension of this ubiquitous scaling law is still lacking. Here we show that a dynamical approach is crucial: during their evolution, some systems are attracted towards Zipf's law, while others presents Zipf's law only temporarily and, therefore, spuriously. A truly Zipfian dynamics is characterized by a dynamical constraint, or coherence, among the parameters of the generating PDF, and the number of elements in the system. A clear-cut example of such coherence is natural language. Our framework allows us to derive some quantitative results that go well beyond the usual Zipf's law: i) earthquakes can evolve only incoherently and thus show Zipf's law spuriously; this allows an assessment of the largest possible magnitude of an earthquake occurring in a geographical region. ii) We prove that Zipfian dynamics are not additive, explaining analytically why US cities evolve coherently, while world cities do not. iii) Our concept of coherence can be used for model selection, for example, the Yule-Simon process can describe the dynamics of world countries' GDP. iv) World cities present spurious Zipf's law and we use this property for estimating the maximal population of an urban agglomeration.

physics.soc-ph↗

arXiv2019

Economic Complexity: why we like "Complexity weighted diversification"

A recent paper by Hausmann and collaborators (1) reaches the important conclusion that Complexity-weighted diversification is the essential element to predict country growth. We like this result because Complexity-weighted diversification is precisely the first equation of the Fitness algorithm that we introduced in 2012 (2,3). However, contrary to what is claimed in (1), it is incorrect to say that diversification is contained also in the ECI algorithm (4). We discuss the origin of this misunderstanding and show that the ECI algorithm contains exactly zero diversification. This is actually one of the reasons for the poor performances of ECI which leads to completely unrealistic results, as for instance, the derivation that Qatar or Saudi Arabia are industrially more competitive than China (5,6). Another important element of our new approach is the representation of the economic dynamics of countries as trajectories in the GDPpc-Fitness space (7-10). In some way also this has been rediscovered by Hausmann and collaborators and renamed as "Stream plots", but, given their weaker metrics and methods, they propose it to use it only for a qualitative insight, while ours led to quantitative and successful forecasting. The Fitness approach has paved the way to a robust and testable framework for Economic Complexity resulting in a highly competitive scheme for growth forecasting (7-10). According to a recent report by Bloomberg (9): The new Fitness method, "systematically outperforms standard methods, despite requiring much less data".

econ.GN↗

arXiv2019

Where is your field going? A Machine Learning approach to study the relative motion of the domains of Physics

We propose an original approach to describe the scientific progress in a quantitative way. Using innovative Machine Learning techniques we create a vector representation for the PACS codes and we use them to represent the relative movements of the various domains of Physics in a multi-dimensional space. This methodology unveils about 25 years of scientific trends, enables us to predict innovative couplings of fields, and illustrates how Nobel Prize papers and APS milestones drive the future convergence of previously unrelated fields.

physics.soc-ph↗

arXiv2018

The role of complex analysis in modeling economic growth

Development and growth are complex and tumultuous processes. Modern economic growth theories identify some key determinants of economic growth. However, the relative importance of the determinants remains unknown, and additional variables may help clarify the directions and dimensions of the interactions. The novel stream of literature on economic complexity goes beyond aggregate measures of productive inputs, and considers instead a more granular and structural view of the productive possibilities of countries, i.e. their capabilities. Different endowments of capabilities are crucial ingredients in explaining differences in economic performances. In this paper we employ economic fitness, a measure of productive capabilities obtained through complex network techniques. Focusing on the combined roles of fitness and some more traditional drivers of growth, we build a bridge between economic growth theories and the economic complexity literature. Our findings, in agreement with other recent empirical studies, show that fitness plays a crucial role in fostering economic growth and, when it is included in the analysis, can be either complementary to traditional drivers of growth or can completely overshadow them.

econ.GN↗

arXiv2018

PopRank: Ranking pages' impact and users' engagement on Facebook

Users online tend to acquire information adhering to their system of beliefs and to ignore dissenting information. Such dynamics might affect page popularity. In this paper we introduce an algorithm, that we call PopRank, to assess both the Impact of Facebook pages as well as users' Engagement on the basis of their mutual interactions. The ideas behind the PopRank are that i) high impact pages attract many users with a low engagement, which means that they receive comments from users that rarely comment, and ii) high engagement users interact with high impact pages, that is they mostly comment pages with a high popularity. The resulting ranking of pages can predict the number of comments a page will receive and the number of its posts. Pages impact turns out to be slightly dependent on pages' informative content (e.g., science vs conspiracy) but independent of users' polarization.

cs.SI↗

arXiv2017

Unfolding the innovation system for the development of countries: co-evolution of Science, Technology and Production

We show that the space in which scientific, technological and economic developments interplay with each other can be mathematically shaped using pioneering multilayer network and complexity techniques. We build the tri-layered network of human activities (scientific production, patenting, and industrial production) and study the interactions among them, also taking into account the possible time delays. Within this construction we can identify which capabilities and prerequisites are needed to be competitive in a given activity, and even measure how much time is needed to transform, for instance, the technological know-how into economic wealth and scientific innovation, being able to make predictions with a very long time horizon. Quite unexpectedly, we find empirical evidence that the naive knowledge flow from science, to patents, to products is not supported by data, being instead technology the best predictor for industrial and scientific production for the next decades.

econ.GN↗

arXiv2017

Economic Complexity: "Buttarla in caciara" vs a constructive approach

This note is a contribution to the debate about the optimal algorithm for Economic Complexity that recently appeared on ArXiv [1, 2] . The authors of [2] eventually agree that the ECI+ algorithm [1] consists just in a renaming of the Fitness algorithm we introduced in 2012, as we explicitly showed in [3]. However, they omit any comment on the fact that their extensive numerical tests claimed to demonstrate that the same algorithm works well if they name it ECI+, but not if its name is Fitness. They should realize that this eliminates any credibility to their numerical methods and therefore also to their new analysis, in which they consider many algorithms [2]. Since by their own admission the best algorithm is the Fitness one, their new claim became that the search for the best algorithm is pointless and all algorithms are alike. This is exactly the opposite of what they claimed a few days ago and it does not deserve much comments. After these clarifications we also present a constructive analysis of the status of Economic Complexity, its algorithms, its successes and its perspectives. For us the discussion closes here, we will not reply to further comments.

econ.GN↗

arXiv2017

Why we like the ECI+ algorithm

Recently a measure for Economic Complexity named ECI+ has been proposed by Albeaik et al. We like the ECI+ algorithm because it is mathematically identical to the Fitness algorithm, the measure for Economic Complexity we introduced in 2012. We demonstrate that the mathematical structure of ECI+ is strictly equivalent to that of Fitness (up to normalization and rescaling). We then show how the claims of Albeaik et al. about the ability of Fitness to describe the Economic Complexity of a country are incorrect. Finally, we hypothesize how the wrong results reported by these authors could have been obtained by not iterating the algorithm.

econ.GN↗

arXiv2017

Coherent diversification in corporate technological portfolios

We study the relationship between firms' performance and their technological portfolios using tools borrowed from the complexity science. In particular, we ask whether the accumulation of knowledge and capabilities related to a coherent set of technologies leads firms to experience advantages in terms of productive efficiency. To this end, we analyzed both the balance sheets and the patenting activity of about 70 thousand firms that have filed at least one patent over the period 2004-2013. From this database it is possible to define a measure of the firms' coherent diversification, based on the network of technological fields, and relate it to the firms' perfomance in terms of labor productivity. Such a measure favors companies with a diversification structure comprising blocks of closely related fields over firms with the same breadth of scope, but a more scattered diversification structure. We find that the coherent diversification of firms is quantitatively related to their economic performance and captures relevant information about their productive structure. In particular, we prove on a statistical basis that a naive definition of technological diversification can explain labor productivity only as a proxy of size and coherent diversification. This approach can be used to investigate possible synergies within firms and to recommend viable partners for merging and acquisitions.

econ.GN↗

arXiv2017

The complex dynamics of products and its asymptotic properties

We analyse global export data within the Economic Complexity framework. We couple the new economic dimension Complexity, which captures how sophisticated products are, with an index called logPRODY, a measure of the income of the respective exporters. Products' aggregate motion is treated as a 2-dimensional dynamical system in the Complexity-logPRODY plane. We find that this motion can be explained by a quantitative model involving the competition on the markets, that can be mapped as a scalar field on the Complexity-logPRODY plane and acts in a way akin to a potential. This explains the movement of products towards areas of the plane in which the competition is higher. We analyse market composition in more detail, finding that for most products it tends, over time, to a characteristic configuration, which depends on the Complexity of the products. This market configuration, which we called asymptotic, is characterized by higher levels of competition.

econ.GN↗

arXiv2016

What do central counterparties default funds really cover? A network-based stress test answer

In the last years, increasing efforts have been put into the development of effective stress tests to quantify the resilience of financial institutions. Here we propose a stress test methodology for central counterparties based on a network characterization of clearing members, whose links correspond to direct credits and debits. This network constitutes the ground for the propagation of financial distress: equity losses caused by an initial shock with both exogenous and endogenous components reverberate within the network and are amplified through credit and liquidity contagion channels. At the end of the dynamics, we determine the vulnerability of each clearing member, which represents its potential equity loss. We apply the proposed framework to the Fixed Income asset class of CC&G, the central counterparty operating in Italy whose main cleared securities are Italian Government Bonds. We consider two different scenarios: a distributed, plausible initial shock, as well as a shock corresponding to the cover 2 regulatory requirement (the simultaneous default of the two most exposed clearing members). Although the two situations lead to similar results after an unlimited reverberation of shocks on the network, the distress propagation is much more hasty in the latter case, with a large number of additional defaults triggered at early stages of the dynamics. Our results thus show that setting a default fund to cover insolvencies only on a cover 2 basis may not be adequate for taming systemic events, and only very conservative default funds, such as CC&G's one, can face total losses due to the shock propagation. Overall, our network-based stress test represents a refined tool for calibrating default fund amounts.

q-fin.RM↗