Forecasting recovery rates on non-performing loans with machine learning

We compare the performance of a wide set of regression techniques and machine-learning algorithms for predicting recovery rates on non-performing loans, using a private database from a European debt collection agency. We find that rule-based algorithms such as Cubist, boosted trees, and random forests perform significantly better than other approaches. In addition to loan contract specificities, predictors that refer to the bank recovery process — prior to the portfolio’s sale to a debt collector — are also shown to enhance forecasting performance. These variables, derived from the time series of contacts to defaulted clients and client reimbursements to the bank, help all algorithms better identify debtors with different repayment ability and/or commitment, and in general those with different recovery potential.     

The Austrian current account deficit: Driven by twin deficits or by intertemporal expenditure allocation?

The evidence presented in the paper rejects the twin deficit hypothesis for the Austrian current account balance during the last two decades. The results are based on an estimate of a vector error correction model including quarterly data for the current account balance and potentially relevant variables driving its dynamics. We compute the variance decomposition of the current account's forecast error and its generalized impulse responses to shocks in the innovations of the system. The results in favor of intertemporal expenditure reallocation cannot be reproduced within a second analysis including the current account and a measure of net output, however. The estimated implicit current account balance, interpreted as the discounted expected change in future net output, does not follow the actual behaviour of the current account. First version received: June 1999/Final version received: March 2001     

Endogenous structural change and crisis in a multiple time-scales growth model

The slow and endogenous twist of economic macro-structure makes up an important evolutionary feature of capitalist economies, and may be at the root of structural crisis. In this line, a Goodwinian growth model with increasing returns and profit-sharing that tries to picture a simple scenario of the seventies crisis is considered. It is shown that the exhaustion of the Kaldor-Verdoorn “productivity law” can entail, in a nonlinear framework, a “catastrophic” bifurcation from a “high” to a “low” growth path. Slow/fast dynamical systems then allow one to formalize a multiple time-scales dynamics where the growth path is shaped by the structural framework in which it takes place, but has also a long -un feedback. Structural change and crisis appear as long term and endogenous outcomes.     

The Geopolitics of Protected Areas

ABSTRACT

The conservation enterprise is embedded in ideas of the environment through which it promotes a vision of the world and the relations between the non-human and human. The papers in this forum analyse conservation from various vantage points to draw the links between geopolitics and conservation. The authors use three themes to demonstrate these links. The first theme draws on the concept of environmentality to show the mobilization of ecological rationalities and power towards the creation of protected areas. The second pays attention to networks formed across the distance, and how they influence the location and governance of protected areas. The third focuses on the strategies the conservation lobby uses to align local identities with global conservation ideals and goals. Collectively, these themes highlight features of conservation geopolitics.     

The effects of perceived value on loyalty: the moderating effect of market orientation adoption

This paper aims to identify the moderating effect of service firms’ adoption of market orientation on key variables of consumer behavior, namely perceived value and loyalty. The study took a business-to-customer perspective. First, the adoption of market orientation was measured, from the firm’s point of view. Second, customer perceptions were analyzed, using the two variables perceived value and loyalty. The sample comprised 100 service firms and 572 of their customers. The present work provides original insights, identifying that the effect of perceived value on loyalty depends on other variables external to the consumer, such as the market orientation approach.     

Utilizing environmental information and pricing strategies to reduce externalities of tourism: the case of invasive species in the Galapagos

The increase in demand for nature-based tourism brings economic and educational benefits but risks the introduction of invasive species. Increasing the length of tourist trips can better balance these benefits and risks by maintaining revenues while reducing the number of unique contacts with tourists. Changing the relative prices of trips can induce tourists to take longer trips. We hypothesized that providing information about the negative externalities of tourism could improve the effectiveness of such pricing strategies.

We administered one of two discrete choice surveys to tourists considering a trip to the Galapagos. One of the surveys described the Galapagos as a fragile ecosystem susceptible to invasive species; the second described it as a standard nature-based destination. For each sample, we estimated the probability of the tourist choosing a short versus long trip, given the tourist's personal information and trip options presented to him. We then simulated the demand for trips using three pricing strategies. We found that providing information on invasive species significantly increased the efficacy of strategic pricing. We propose using a two-prong approach to tourism management: educate potential tourists about the islands’ vulnerabilities, and simultaneously increase the per-day cost of short trips relative to that of longer trips.     

The World Market for Labor and the World Market for Industrial Sites

At the center of the on-going debate about the U.S. Social Security system is the question of whether the way the system is financed can cope with the future challenges posed by the retiring Baby Boom generation. The "reformers" suggest changing the design of the system by moving to fully funded defined contribution retirement plans. Others argue that the so-called demographic problems are being used as an excuse to privatize the system. But both sides spend almost all of their energy and time figuring out the timing of insolvency of the system and the validity of the assumptions made in each forecast. In contrast, the present study closely examines the changing macroeconomic dynamics of the system since the 1960s. The analysis shows that undermining of the system is caused not by demographic changes or financing mechanisms but by low wages and medical inflation.     

Do brain drain and poverty result from coordination failures?

The bidirectional causal links between high-skilled emigration and poverty can give rise to multiple equilibria and coordination failures. Two countries sharing identical characteristics may end up in either a “low poverty-low brain drain” equilibrium or in a “high poverty-high brain drain” equilibrium. In this paper, we build a model which endogenizes high-skilled emigration and economic performances in order to derive the conditions under which multiplicity occurs. After identifying country-specific parameters, we find that in the majority of developing countries, the best equilibrium is selected and that the observed brain drain is inevitable. In 22 small developing countries however, the worse equilibrium prevails, implying that poverty and brain drain are increased by coordination failure. These countries require appropriate development policies, such as a temporary subsidization of the repatriation of their high-skilled expatriates. Our results are robust to the inclusion of a brain gain mechanism.     

Generating Enhanced Fishery Rents by Internalizing Product Quality Characteristics

This paper demonstrates howadditional rents are generated in a fisherycharacterized by intraseasonal variation infish characteristics, including size,condition, and composition. Based on anexpanded conceptual model of the optimalharvest rule, fish characteristics affect preand post harvest production yields and outputprices. A dynamic empirical model, which uses asystem of quality characteristics and anhedonic equation, illustrates the complexrelationships and management choices associatedwith internalizing seafood qualitycharacteristics in a hake fishery. The modelretains the regulated open access managementsystem, but controls intertemporal andintersectoral quotas, production portfolios,and total allowable catch. Results demonstratethat including revenue-side effects frominternalizing fish quality can generatesignificantly greater rents and reduce therelative benefits of increased productionyields. If excluded, bioeconomic models canunderestimate the level of regulatory rentdissipation and overemphasize managementobjectives such as full utilization, whichcould misdirect processing decisions and resultin a suboptimal resource management plan.Implications for data collection,multidisciplinary analysis, and improvements inmarine resource management are discussed.