Marcos M. López de Prado: Machine learning for asset managers

Financial Markets and Portfolio Management -     

New product adoption in social networks: Why direction matters

Marketing managers and researchers generally agree that analyzing data from social networks and using them to influence consumers' purchase decisions are useful strategies. However, not all social network data may identify the most influential customers. This empirical study of more than 300 students reveals the low explanatory power of friendship networks (e.g., Facebook) and undirected-advice networks (e.g., LinkedIn). Only directed-advice networks (e.g., Google +) clearly identify influential consumers. In addition, the results challenge conventional wisdom that firms should target advisers assuming that they have the strongest influence on new product adoption. This study contradicts this common assumption and reveals that structural equivalence drives product adoption more than cohesion because advisees' adoption pressures advisers to purchase the product as well. Finally, the study shows the value of social network data beyond the traditional ego-centric psychographic metrics, such as innovativeness or opinion leadership.     

The Impact of Search and Recommendation Systems on Sales in Electronic Commerce

The Internet and related technologies have vastly expanded the variety of products that can be profitably promoted and sold by online retailers. Furthermore, search and recommendation tools reduce consumers’ search costs in the Internet and enable them to extend their search from a few easily found best-selling products (blockbusters) to a large number of less frequently selling items (niches). As a result, Long Tail sales distribution patterns emerge that illustrate an increasing demand in niches. We show in this article how different classes of search and recommendation tools affect the distribution of sales across products, total sales, and consumer surplus. We hereby use an agent-based simulation which is calibrated based on real purchase data of a video-on-demand retailer. We find that a decrease in search costs through improved search technology can either shift demand from blockbusters to niches (search filters and recommendation systems) or from niches to blockbusters (charts and top lists). We break down demand changes into substitution and additional consumption and show that search and recommendation technologies can lead to substantial profit increases for retailers. We also illustrate that decreasing search costs through search and recommendation technologies always lead to an increase in consumer surplus, suggesting that retailers can use these technologies as competitive advantage.     

An Algorithmic Approach to Optimal Asset Liquidation Problems

This paper examines discrete-time optimal control problems arising in the context of optimal asset liquidation using recently published algorithms and code. We address these questions within a realistic framework, assuming that the order placement decisions must be adapted dynamically. Furthermore, we show how a duality-based technique can be used to assess the quality of our numerical solution.     

Pricing electricity risk by interest rate methods

We address a method for pricing electricity contracts based on the valuation of the ability to produce power, which is considered as the true underlying factor for electricity derivatives. This approach shows that an evaluation of free production capacity provides a framework where a change-of-numeraire transformation converts the electricity forward market into the common settings for money market modelling. Using the toolkit of interest rate theory, we derive explicit option pricing formulas.     

Free automotive unions,industrial work and precariousness in provincial Russia

This article draws on ethnographic work carried out since 2009 on workers and automotive unions in Kaluga, Russia. The contrast between secure and temporary contract workers in foreign-owned car plants is a focus of activism among emerging alternative trade unions in Kaluga. Workers in both the ‘new’ production-scape of high-tech foreign-owned automotive assembly, and the ‘old’ low-tech Soviet production contexts articulate similar interpretive understandings of what constitutes ‘precarious’ work: lack of autonomy and the lack of a ‘social wage’ generally in labour. We interrogate this through in-depth interviews with unionised and non-unionised workers in the auto sector and other industries locally. A divide emerges between workers who go to work for the car plants, and those who remain in Soviet-types firms and who reject the labour relations model that it offers and which they understand to contrast with a traditional ‘paternalistic’ Russian model.     

Wann kommt die Kostenwende bei der EEG-Umlage?

The apportionment of the German Renewable Energy Sources Act (EEG-Umlage) constitutes a significant portion of the electricity price for domestic and commercial customers. First, the authors outline the implemented apportionment mechanism, the historical development as well as a couple of the lack of misjudgments. Subsequently, they investigate the question whether and when a reduction of the EEG apportionment can be expected. A model based on the current remuneration rules of the EEG, which is validated based on forecasts conducted by the transmission system operators, is used for the calculation of the EEG apportionment. The calculations show that an increase of the EEG levy to over 8?ct/kWh can be expected in the reference case, followed by a reduction from 2025 onwards. In the context of sensitivity calculations, various uncertainty factors are identified, such as the development of the wholesale price or the magnitude of the remuneration. Those factors significantly influence the EEG levy and thus underline the challenges in the development of a reliable forecast.