Prescriptive analytics extends on predictive analytics by allowing to estimate an outcome in function of control variables, allowing as such to establish the required level of control variables for realizing a desired outcome. Uplift modeling is at the heart of prescriptive analytics and aims at estimating the net difference in an outcome resulting from a specific action or treatment that is applied. In this article, a structured and detailed literature survey on uplift modeling is provided by identifying and contrasting various groups of approaches. In addition, evaluation metrics for assessing the performance of uplift models are reviewed. An experimental evaluation on four real-world data sets provides further insight into their use. Uplift random forests are found to be consistently among the best performing techniques in terms of the Qini and Gini measures, although considerable variability in performance across the various data sets of the experiments is observed. In addition, uplift models are frequently observed to be unstable and display a strong variability in terms of performance across different folds in the cross-validation experimental setup. This potentially threatens their actual use for business applications. Moreover, it is found that the available evaluation metrics do not provide an intuitively understandable indication of the actual use and performance of a model. Specifically, existing evaluation metrics do not facilitate a comparison of uplift models and predictive models and evaluate performance either at an arbitrary cutoff or over the full spectrum of potential cutoffs. In conclusion, we highlight the instability of uplift models and the need for an application-oriented approach to assess uplift models as prime topics for further research.

No abstract

Application scorecards allow to assess the creditworthiness of loan applicants and decide on acceptance. The accuracy of scorecards is of crucial importance for minimizing bad debt loss and maximizing returns. In this paper, we extend upon prior benchmarking studies that experimentally compare the performance of classification techniques to discriminate between good and bad applications. We evaluate a range of cost-sensitive learning methods in terms of their ability to boost the profitability of scorecards. These methods allow to take into account the variable misclassification costs that are involved in rejecting good loan applications and accepting bad loan applications.An approach is proposed to estimate these misclassification costs, and various approaches to handle missing credit bureau scores are evaluated. The results of a case study involving a Romanian nonbanking financial institution (NBFI) indicate that cost-sensitive learning complements the existing state-of-the-art scorecard of the NBFI. The best performing cost-sensitive models are found to increase profitability across the three business channels, with a single-digit improvement for two of the channels and a double-digit increase for the other one. The result is partly explained by the default rate, which is higher for this latter channel and therefore o↵ers greater potential for improving profitability.

This paper presents a sentiment analysis solution on tweets using Recurrent Neural Networks (RNNs). The method is can classifying tweets with an 80.74% accuracy rate, considering a binary task, after experimenting with 20 different design approaches. The solution integrates an attention mechanism aiming to enhance the network, with a two-way localization system: at memory cell level and at network level. We present an in-depth literature review for Twitter sentiment analysis and the building blocks that grounded the design decisions of our solution, employed as a core classification component within a sentiment indicator of the SynergyCrowds platform.

Over the last decade, globalization processes have intensified, and as such, global organizations relocated their secondary processes to new spaces specialized in operations (Peck 2018; Oshri, Kotlarsky, and Willcocks 2015). Most of the processes that are being externalized are Business Process Outsourcing (BPO) and Information Technology Outsourcing (ITO) (Oshri, Kotlarsky, and Willcocks 2015). The global outsourcing hotspots are India, China and the Philippines, that concentrate over 80% of outsourced processes. At European level, Central and Eastern Europe has capitalized most of the outsourcing in the West, particularly in regards to German capital (Marin 2018; Dustmann et al. 2014). Almost half (45.4%) of the total foreign investments of German companies is outsourced to Central and Eastern Europe. In Romania 63.7% of the German foreign investments are processes that were outsourced to our country (Marin, Schymik, and Tarasov 2018). As Peck (2018) points out, the logic behind the process is finding the cheapest labor force pools. Initially, outsourcing was focused on industrialized labor, however, now it is mostly skilled and highly skilled workforce that is being outsourced (Pavlínek 2019). Even if it is work performed by white collars, it has a high level of repetitiveness; however, in sectors such as IT there are also R&D operations (Oshri, Kotlarsky, and Willcocks 2015). Cluj is an example of a city whose local economy and workforce composition changed dramatically after the 2008-2010 financial crisis. The city is one of the Central and Eastern European hubs that benefited from the globalization of outsourcing operations. In particular, Cluj-Napoca excels in four transnational fields: Information & Communications Technology, Business Support Services, Engineering, Research & Development and Financial Services. In 2018, Cluj-Napoca was one of the most developed cities in the European Union in the GDP per capita group 19.000 – 27.000 at Purchasing Power Parity, cities that made a credible commitment at European level to promote knowledge, culture and creativity. In particular, participation in global production chains has generated the emergence of two types of internal markets: An internal market for the well-paid labor force employed in internationalized sectors that consumes a series of dedicated products and services: hospitality (restaurants, cafes, bars), food stuffs (meat products, pastries, premium alcoholic products), lifestyle services (hair salons , spas, gyms), cultural services (festivals, theatres, operas), location services (real estate services, interior design services, furniture manufacturing services). A set of markets that serve the global capital in reproducing their location (cleaning services, security, construction of type A office buildings, human resources). Both domestic and internationalized markets are responsible for the impressive development of the city between 2008 and 2018. The GDP of the Cluj Metropolitan Area and the private revenues of companies have doubled in the last decade.