Caterina Liberati

A new prognostic model to predict dropout from the waiting list in cirrhotic candidates for liver transplantation with MELD score <18

The model for end‐stage liver disease (MELD) is used for organ allocation in liver transplantation (LT), but its prognostic performance is less accurate in patients with low score. We assess the outcome of patients with MELD < 18 awaiting LT, finding prognostic variables to identify a high dropout risk.

Subjective Business Polarization: Sentiment Analysis Meets Predictive Modeling

The growth of Internet and the information technology has generated big changes in subjects communication, that, nowadays, occurs through social media or via thematic forums. This produced a surge of information that is freely available: it offers the possibility to companies to evaluate their credibility and to monitor the ”mood” of their markets. The application of Sentiment Analysis (SA) has been proposed in order to extract, via objective rules, positive or negative opinions from (unstructured) texts. Communication literature, instead, highlights how such polarization derives from a subjective evaluations of the texts by the receivers. In business applications the receiver (i.e. marketing manager) is leaded by the values and the mission of the company. In our paper we propose a strategy to fit brand image and company values with a subjective SA, a probabilistic Kernel classifier has been employed to get discrimination rule and to rank classification results.

Structural distortions in the Euro interbank market: The role of ‘key players’ during the recent market turmoil

We study the frictions in the patterns of trades in the Euro money market. We characterize the structure of lending relations during the period of recent financial turmoil. We use network-topology method on data from overnight transactions in the Electronic Market for Interbank Deposits (e-Mid) to investigate on two main issues. First, we characterize the division of roles between borrowers and lenders in long-run relations by providing evidence on network formation at a yearly frequency. Second, we identify the ‘key players’ in the marketplace and study their behaviour. Key players are ‘locally-central banks’ within a network that lend (or borrow) large volumes to (from) several counterparties, while borrowing (or lending) small volumes from (to) a small number of institutions. Our results are twofold. We show that the aggregate trading patterns in e-Mid are characterized by largely asymmetric relations. This implies a clear division of roles between lenders and borrowers. Second, the key players do not exploit their position of network leaders by imposing opportunistic pricing policies. We find that only a fraction of the networks composed by big players are characterized by interest rates that are statistically different from the average market rate throughout the turmoil period.

Advances in credit scoring: combining performance and interpretation in kernel discriminant analysis

Due to the recent financial turmoil, a discussion in the banking sector about how to accomplish long term success, and how to follow an exhaustive and powerful strategy in credit scoring is being raised up. Recently, the significant theoretical advances in machine learning algorithms have pushed the application of kernel-based classifiers, producing very effective results. Unfortunately, such tools have an inability to provide an explanation, or comprehensible justification, for the solutions they supply. In this paper, we propose a new strategy to model credit scoring data, which exploits, indirectly, the classification power of the kernel machines into an operative field. A reconstruction process of the kernel classifier is performed via linear regression, if all predictors are numerical, or via a general linear model, if some or all predictors are categorical. The loss of performance, due to such approximation, is balanced by better interpretability for the end user, which is able to order, understand and to rank the influence of each category of the variables set in the prediction. An Italian bank case study has been illustrated and discussed; empirical results reveal a promising performance of the introduced strategy.

Banking customer satisfaction evaluation: a three-way factor perspective

As management of a national bank wanted to analyze its retail service competition loss probably due to low customer satisfaction, we carried out an empirical study based on a sample of 27,000 retail customers. The survey aimed to analyze retail service weaknesses and to individuate possible recovery actions measuring their effectiveness across different waves (three time lags). We studied a definition of a new dissimilarity measure exploiting a dimension reduction obtained by a three-way factor analysis (TFA). We had previously focused our attention on the limits of this approach related to the geometrical properties of the TFA applied. We introduced a reassessment of the points to adjust the three-way solution according to the quality of representation of the points. This transformation only rescaled the factor scores producing a local adjustment of the point configuration. We then performed a trajectory analysis of the different waves. The results showed the effectiveness of our approach. Therefore, further study of the derivation of a synthetic measure of cluster routes seems appropriate.

A Multivariate Approach to Facebook Data for Marketing Communication

The aim of this paper is to propose a method to explore and synthesize social media data in order to aid businesses to make their communication decisions. The research was conducted at the end of 2014 on 5607 Italian Facebook subjects interested in drugs and health. In this study, we refer to the pharmaceutical market that is characterized by strict legal constraints, which prevent any promotional activities (such as advertising) of companies on prescription drugs. Thus, pharmaceutical businesses tend to promote their corporate brand instead of a single product brand. In such context, social media offer the opportunity to gather customers’ information about their attitudes and preferences, helpful to address marketing activities. Through a multivariate statistical approach on Facebook data, we have highlighted the associations existing between TV channels and users’ profiles. Therefore, depending on the value proposition to promote, every business could choose, first, the target group to reach and, then, the nearest suitable channel where to develop the corporate brand communication.

Dynamic Principal Component Analysis: A Banking Customer Satisfaction Evaluation

An empirical study, based on a sample of 27.000 retail customers, has been curried out: the management of a national bank with a spread network across Italian regions wanted to analyze the loss in competition of its retail services, probably due to a loss in customer satisfaction. The survey has the aim to analyze weaknesses of retail services, individuate possible recovery actions and evaluate their effectiveness across different waves (3 time lags). Such issues head our study towards a definition of a new path measure which exploits a dimension reduction obtained with Dynamic Principal Component Analysis (DPCA). Results which shown customer satisfaction configurations are discussed in the light of the possible marketing actions.

Big data meet pharmaceutical industry: an application on social media data

Big Data are hard to capture, store, search, share, analyze, and visualize. Without any doubts, Big Data represent the new frontier of data analysis, although their manipulation is far to be realized by standard computing machines. In this paper, we present a strategy to process and extract knowledge from Facebook data, in order to address marketing actions of a pharmaceutical company. The case study relies on a large Italians sample, interested in wellness and health care. The results of the study are very sturdy and can be easily replicated in different contexts.

A Latent Growth Curve Analysis in Banking Customer Satisfaction

Customer satisfaction for banking services is, arguably, a construct that develops and changes over time for a number of different endogenous and exogenous factors (modification of customers contract terms, transparency of banking transactions and financial services, bank charges, customer relationships, changes of market conditions an so on). Measuring change requires a longitudinal perspective, with repeated measurements on the same individuals across multiple time points. Investigating individual differences in change may be of great practical interest for the strategic decisions of the general management of banking companies. Using a Latent Growth Curve Model, the aim of this paper is to analyze the dynamic process in satisfaction of meaningful sub groups of customers of an Italian bank company.

Dynamic Customer Satisfaction and Measure of Trajectories: A Banking Case

The most important company asset seems to be Customer Satisfaction (CS), which banks, in the recent years, have frequently analyzed. For reaching such target, a dynamic Factor Analysis offers an effective way of merging information about clients and their preferences evolution. In our work we performed a dynamic Customer Satisfaction study, by means of a three-way factorial analysis, and we also introduced a new index of shift and shape (SSI), to synthesize information about every customer, cluster or typology. We considered a national bank case, with spread network, evaluating results provided by a questionnaire framed according to the SERVQUAL model. The information employed was obtained via a Customer Satisfaction survey repeated three times (waves). We performed the dynamic factorial model and we illustrated the usage of SSI as a new measure of trajectories’ dissimilarity. Finally, we showed our results which highlight promising performances of our index.