A random forest-based model for crypto asset forecasts in futures markets with out-of-sample prediction

In this study, a price prediction model for futures markets of crypto assets is presented. Random Forest was used to study three scenarios as a function of input variables: technical indicators, candlestick patterns and both simultaneously. In turn, the model parameters, the time intervals, and the most suitable investment horizons were studied. In addition to showing the results from the model, a one-year out-of-sample prediction was simulated. The entire year of 2020 was chosen because the three possible stock market scenarios occurred in this year: a sideways market, a bear market resulting from the global pandemic and an end-of-year bull market. Last, this out-of-sample simulation was analyzed as a real operation, that is, by retraining the model after each new collection of data, so that the model had the maximum information at all times. In conclusion, using candlestick patterns instead of technical indicators, improves the efficiency of the results.     

Measuring financial soundness around the world: A machine learning approach

We use a fully data-driven approach and information provided by the IMF’s financial soundness indicators to measure the condition of a country’s financial system around the world. Given the nature of the measurement problem, we apply different versions of principal component analysis (PCA) to deal with the presence of strong cross-sectional and time dependence in the data due to unobserved common factors. Using this comprehensive sample and various statistical methods, we produce an alternative data-driven measure of financial soundness that provides policy makers and financial institutions with a monitoring and policy tool that is easy to implement and update. We validate our index by using alternative macroeconomic factors, confirming its predictive power. Our index captures important aspects of financial intermediation around the world.     

Amazon forest on the edge of collapse in the Maranhão State,Brazil

The year 2019 in Brazil was marked by environmental setbacks, which catalyzed the increase of illegal deforestation and fire rates in the Brazilian Amazon. In the Amazon region of Maranhão state, original forest cover diminished from 25 % (24,700 km²) in 2016 to 24 % (23,967 km²) in 2019, and 6,038 km² of remaining forests were degraded by fires and/or illegal logging – processes related to high levels of violence against indigenous and rural communities. Almost half of all deforested areas in the region (36,060 km²) are considered a global restoration hotspot, however secondary vegetation remains unprotected and 8,294 km² were cleared between 2014 and 2018. Due to uncontrolled deforestation and fragmentation, Maranhão has no more forest core areas (outside protected areas) with the minimum size to ensure sustainable forest management practices for timber production. New policies at the state level must promote old-growth and secondary forest conservation and restoration. However, the trends point to the opposite direction: the Ecological-Economic Zoning (ZEE) allows the reduction of forest protection and the State Forest Policy reinforces federal legislation setbacks. The Amazon region of Maranhão state has forest aptitude, and forest and agroforestry product chains would bring social and environmental benefits, making them the best opportunity for sustainable economic development in the region. Therefore, the forest must be re-planted for the benefit of people and nature.     

Context sensitive policy instruments: A multi-criteria decision analysis for safeguarding forest habitats in Southwestern Finland

Environmental and conservation decisions are often complex, which results in complexity also in policy assessments. Conservation decisions have implications for different stakeholders and typically draw on multidisciplinary knowledge bases, incorporating natural, physical and social sciences, politics and ethics. Multi-Criteria Decision Analysis (MCDA) is a potentially important tool for supporting conservation policy decisions. This article reports a spatially referenced MCDA of policy instrument scenarios for conserving forest biodiversity in Southwestern Finland. The effects of the realistic policy instruments designed in dialogue with stakeholders included voluntary permanent conservation, enforced spatially concentrated permanent conservation, voluntary permanent conservation with active nature management, and voluntary temporary conservation. These instruments were compared by combining forest-owner survey, MCDA and ex ante impact evaluation. The main objective was to find the forest biodiversity conservation instrument that would produce the highest total benefit. The effects of the different instruments were evaluated with ecological, economic, social, and institutional criteria after a 20-year time period. The results showed minor differences between the instruments, with voluntary permanent and voluntary temporary conservation producing the largest total benefit. Despite the small differences, the analysis was robust in showing that voluntary instruments were more favourable than enforced permanent conservation.     

The politics of environmental market instruments: Coalition building and knowledge filtering in the regulation of forest certificates trading in Brazil

Market instruments for environmental governance have a foundation in an economic theorythat claims to be universal and atemporal, but their materialization in practice always takes place in specific socioeconomic and political contexts. The Brazilian trade in forest certificates (CRA) is a new market instrument that allows farmers that have deforested illegally prior to 2008 to become compliant by acquiring certificates from other farmers that conserve a forest area beyond legal requirements. Even though the CRA market has been praised as an innovative environmental policy, it is still unclear whether it will be implemented even after more than two decades of political debate, congressional approval of legislation and substantial investments in new supporting systems. This research paper aims to analyze the materialization of this market by reconstructing how policy participants form advocacy coalitions (i.e. environmental protection, market viability and agricultural consolidation) to advance their interests. Our results show that advocacy coalitions filter (i.e. absorb, reject or transform) new ideas, experiences and knowledge in order to influence the regulations for forest certificate trading. In doing so, they often combine positions, form new alliances and merge with other advocacy coalitions in accordance with the interests of their constituents. These fluid allegiances within and between coalitions explain why market materialization remains ambiguous and unlikely to become operational in the near future.     

Changes in Brazil’s Forest Code can erode the potential of riparian buffers to supply watershed services

In Brazil, the Forest Code requires landholders to maintain fixed-width buffers of native vegetation along watercourses – legally called Areas of Permanent Preservation (APPs). In 2012, agricultural activities started to be partially allowed in APPs, but only if best management practices on soil and water conservation are adopted and if a narrow buffer strip with native vegetation is restored adjacently to the watercourse. In this paper, we present a modeling framework to investigate the capacity of legal compliant APPs to supply watershed services (erosion control and stream bank stabilization) in a 2,200 ha watershed in São Paulo State, Brazil. Our results suggest that the narrower the riparian buffer the lower the control of soil erosion dynamic within APPs, and that riparian buffers smaller than 8 m can act as a source of sediments to streams. The adoption of best management practices can contribute to controlling soil erosion within APPs but the presence of native forests in the first 15 m is necessary to guarantee equivalent protection to streams when compared to APPs completely covered by forests. Moreover, we observed that forest restoration within APPs helped to reduce the average soil loss of the watershed by only 20 %, compared to a reduction of 55 % when best practices are implemented in all watershed agricultural areas. We conclude that (i) the reduced requirements for APP restoration may contribute to stream sedimentation, which will likely affect the supply of watershed services by stream ecosystems; (ii) the implementation of best management practices in APPs will not have the same effect as native forests to reduce stream sedimentation; and (iii) the adoption of best management practices in all agricultural production areas – and not only within APPs as required by law – is the best strategy to promote the supply of watershed services to society.     

The impact of exurban development on forested areas in Kurgan City,Russia

Exurban communities—a significant form of urban sprawl—can transform natural land cover. Exurban development refers to an expansion of communities located outside a city and its suburbs. One of the main reasons these settlements develop is a desire by residents to live closer to nature and developers’ recognition of the profitability of addressing this desire. Additionally, exurbs can become prosperous regions settled by people with high income. However, exurban development not only directly affects community patterns, but also species patterns, habitat reduction and disconnection, as well as land cover and land use alterations. The purpose of this paper is a quantitative analysis of the land cover transformation and forest fragmentation in Post-Soviet Russia, based on an empirical case study of the city of Kurgan. This case study also contributes to the overall research of urban sprawl in Russian provinces by adding to the discussion of homeowners’ behavior, regional environmental policies, and their role concerning the impacts of exurban settlements on the natural environment. This paper uses remote sensing imagery, census data, and primary data to analyze land cover change due to the emergence of exurban communities around Kurgan, Russia, with specific emphasis on the changes to native vegetation resulting from human behavior and stakeholder preferences.     

Reforestation and smallholder livelihoods in the humid tropics

Smallholder livelihoods and the restoration of tropical forests are intimately intertwined. To address the question of how reforestation affects livelihoods and how they in turn affect reforestation, a meta-synthesis was undertaken of 339 scientific publications identified from a systematic literature search. This study is focused on smallholders in the humid tropics, and uses the Sustainable Livelihoods Framework, which was developed by the UK Department for International Development as the framework for analysis. The links between reforestation and livelihoods are found to be diverse and highly interconnected. Reforestation is only one of a smallholder’s activities and typically forms part of a mosaic of land uses across a landscape. Therefore, reforestation should be designed, managed and evaluated under the perspective of a diverse livelihood portfolio, and not as a single activity isolated from other portfolio components, especially under current landscape approaches. It is important for reforestation to be a complementary rather than a competitive livelihood activity. Reforestation has great potential to address poverty, and to increase smallholder socio-ecological resilience and local social equity. However, reforestation outcomes are often suboptimal. Assessing smallholder capacity and the surrounding environment prior to reforestation, and addressing limiting local capacities and conditions in a timely manner, may enhance the likelihood of optimal benefits.     

“柏广新现象”集中体现了林业领域的浮躁心态

被媒体炒得沸沸扬扬的林木市场成熟理论林木市场价格和市场需求达到最大,这是有悖于经济学常识的,不管从命名还是内容等方面看该理论都是个伪命题,经不起理论的推敲和实践的检验。在该理论的验收会上,实际上大多数学者更是强调了中国商品林发展要尊重市场经济规律,而没有给该理论太多的肯定。被媒体超常吹捧的柏理论不是一个孤立的事件,它昭示着多种歪风邪气,在本质上揭示了中国林业界浮躁的心态。     

Forecasting the German forest products trade: A vector error correction model

In the forest sector often very complex models are used that take into account a variety of factors. In addition to variables that describe the natural production of wood, into these models flow among others also such variables that depict nature conservation legislation, market contexts, etc. The limited availability of large amounts of data and more particularly of precise data to all these subject areas considerably weakens the validity of the models. Our study therefore takes up the challenge to develop a model, as simple as possible, that can help to estimate export and import volumes as well as export and import prices of raw timber in Germany. To this end, we apply the technique of time series analysis and develop a simple model that allows for short-term and medium-term forecasting in the German forest sector. We show that using a vector error correction model (VECM) can succeed in a relatively simple modelling of future quantities and prices of raw timber for Germany.