What drives a donor? A machine learning-based approach for predicting responses of nonprofit direct marketing campaigns

Direct marketing campaigns are one of the main fundraising sources for nonprofit organizations and their effectiveness is crucial for the sustainability of the organizations. The response rate of these campaigns is the result of the complex interaction between several factors, such as the theme of the campaign, the month in which the campaign is launched, the history of past donations from the potential donor, as well as several other variables. This work, applied on relevant data gathered from the World Wide Fund for Nature Italian marketing department, undertakes different data mining approaches in order to predict future donors and non-donors, thus allowing for optimization in the target selection for future campaigns, reducing its overall costs. The main challenge of this research is the presence of thoroughly imbalanced classes, given the low percentage of responses per total items sent. Different techniques that tackle this problem have been applied. Their effectiveness in avoiding a biased classification, which is normally tilted in favor of the most populated class, will be highlighted. Finally, this work shows and compares the classification results obtained with the combination of sampling techniques and Decision Trees, ensemble methods, and Artificial Neural Networks. The testing approach follows a walk-forward validation procedure, which simulates a production environment and reveals the ability to accurately classify each future campaign.     

Skills scarcity and export intensity

We describe a model of trade with skills-based product differentiation and non-proportional trade costs that predicts a positive correlation between firms' export intensity, the price of their exports and the wages they pay to their workers. In equilibrium, firms that employ workers with comparatively scarcer skills export a larger proportion of their output, pay higher wages and charge higher prices. In line with empirical evidence, the model predicts that trade liberalization can cause the distribution of earnings to become more polarized, with patterns that reflect the heterogeneous effects of trade liberalization on firms' export performance.     

Tax morale,fiscal capacity,and war

This paper studies the effects of mobilization for war on the development of fiscal capacity and the values of tax compliance (tax morale). We propose a dynamic setting where governments may invest resources to improve the efficiency of the fiscal apparatus and the citizens' tax morality in order to raise the necessary revenues for the defense against a threat (external or internal), and parents optimally choose to transmit their preferences of tax compliance to children. Despite fiscal capacity and tax morale are initially substitutes, we show how a dynamic complementarity may arise in equilibrium from a more efficient transmission of the values of tax compliance in countries with high fiscal capacity, and this may explain why they tend to move together over time. Under reasonable conditions, we obtain that the effect of a higher threat of war on the steady-state level of the culture of tax compliance is negative when fiscal capacity is relatively low, and positive when the latter is large. We show cross-country evidence based on war frequency, fiscal capacity, and tax morale that is consistent with the results of our theory.     

You can't be what you can't see: The role of gender in the intergenerational transmission of entrepreneurship

In this paper, we investigate how the intergenerational transmission of entrepreneurship varies between sons and daughters and whether such a process depends on living in a country characterized by a high gender gap. Using the Survey of Health, Ageing, and Retirement in Europe data set, we find that the effect on daughters' entrepreneurial choices of having an entrepreneur as father is lower than the one on sons only in countries with a high gender gap. Moreover, it is just in countries with high gender inequality that the effect of having an entrepreneurial mother is different between sons and daughters, with the impact being positive for daughters only. We also develop an individual-level indicator of gender gap within countries that corroborates our findings, which we interpret as evidence of the presence of a role-modeling mechanism. However, we find evidence of convergence across time of the intergenerational transmission process to the gender-independent transfer typical of more gender-equal countries.     

Food for tourists—determinants of an image

Eating is a physical necessity, but catering services and food image are also very important ingredients of cultural tourism. Food and tourism are increasingly being combined, e.g. in agri‐tourism, wine tours and the sale of food products as souvenirs. However, as this paper illustrates, the development and standards of food for tourists are not determined uniformly by tourism policies, but more significantly by national economic, agricultural and food policies. A comparison between Denmark and Italy illustrates core elements in food cultures. Particularly in Denmark, food production is a major economic activity, and the power of the agricultural and food processing industries has in many cases compromised the quality image. In Italy, on the other hand, food policies and traditions, which give a high priority to freshness, intrinsically allow consumers to stay in control of food to a much larger extent than in Denmark. In both countries, a concentration of tourists in space and time tends to result in a decline of food profile. The paper concludes that only residents are in a position to put a more permanent pressure on food suppliers, and only if they are given the appropriate instruments. Further improvement of the food heritage in both countries (but especially in Denmark) will have to include a reconsideration, and probably changes, in food policies in more global terms. Copyright © 2000 John Wiley & Sons, Ltd.