Using customer lifetime value to improve the prediction of bank deposit subscription in telemarketing campaigns

Customer lifetime value (LTV) enables using client characteristics, such as recency, frequency and monetary (RFM) value, to describe the value of a client through time in terms of profitability. We present the concept of LTV applied to telemarketing for improving the return-on-investment, using a recent (from 2008 to 2013) and real case study of bank campaigns to sell long- term deposits. The goal was to benefit from past contacts history to extract additional knowledge. A total of twelve LTV input variables were tested, un- der a forward selection method and using a realistic rolling windows scheme, highlighting the validity of five new LTV features. The results achieved by our LTV data-driven approach using neural networks allowed an improvement up to 4 pp in the Lift cumulative curve for targeting the deposit subscribers when compared with a baseline model (with no history data). Explanatory knowledge was also extracted from the proposed model, revealing two highly relevant LTV features, the last result of the previous campaign to sell the same product and the frequency of past client successes. The obtained results are particularly valuable for contact center companies, which can improve pre- dictive performance without even having to ask for more information to the companies they serve.

Personalized-based dietary recommendation for weightlifting

Dissertação de mestrado integrado em Engenharia Eletrónica Industrial e Computadores

Programa com abordagem probabilística do sistema de avaliação de qualidade de taludes Slope Quality Index (SQI)

Dissertação de mestrado integrado em Engenharia Civil

Simulation of humidity fields in concrete: experimental validation and parameter estimation

The moisture content in concrete structures has an important influence in their behavior and performance. Several vali-dated numerical approaches adopt the governing equation for relative humidity fields proposed in Model Code 1990/2010. Nevertheless there is no integrative study which addresses the choice of parameters for the simulation of the humidity diffusion phenomenon, particularly in concern to the range of parameters forwarded by Model Code 1990/2010. A software based on a Finite Difference Method Algorithm (1D and axisymmetric cases) is used to perform sensitivity analyses on the main parameters in a normal strength concrete. Then, based on the conclusions of the sensi-tivity analyses, experimental results from nine different concrete compositions are analyzed. The software is used to identify the main material parameters that better fit the experimental data. In general, the model was able to satisfactory fit the experimental results and new correlations were proposed, particularly focusing on the boundary transfer coeffi-cient.

Using data mining for prediction of hospital length of stay: an application of the CRISP-DM Methodology

Hospitals are nowadays collecting vast amounts of data related with patient records. All this data hold valuable knowledge that can be used to improve hospital decision making. Data mining techniques aim precisely at the extraction of useful knowledge from raw data. This work describes an implementation of a medical data mining project approach based on the CRISP-DM methodology. Recent real-world data, from 2000 to 2013, were collected from a Portuguese hospital and related with inpatient hospitalization. The goal was to predict generic hospital Length Of Stay based on indicators that are commonly available at the hospitalization process (e.g., gender, age, episode type, medical specialty). At the data preparation stage, the data were cleaned and variables were selected and transformed, leading to 14 inputs. Next, at the modeling stage, a regression approach was adopted, where six learning methods were compared: Average Prediction, Multiple Regression, Decision Tree, Artificial Neural Network ensemble, Support Vector Machine and Random Forest. The best learning model was obtained by the Random Forest method, which presents a high quality coefficient of determination value (0.81). This model was then opened by using a sensitivity analysis procedure that revealed three influential input attributes: the hospital episode type, the physical service where the patient is hospitalized and the associated medical specialty. Such extracted knowledge confirmed that the obtained predictive model is credible and with potential value for supporting decisions of hospital managers.

High strain rate constitutive modeling forhistorical structures subjected to blast loading

Doctoral Thesis Civil Engineering

On the Hill estimator: a comparison of methods

Extreme value theory (EVT) deals with the occurrence of extreme phenomena. The tail index is a very important parameter appearing in the estimation of the probability of rare events. Under a semiparametric framework, inference requires the choice of a number k of upper order statistics to be considered. This is the crux of the matter and there is no definite formula to do it, since a small k leads to high variance and large values of k tend to increase the bias. Several methodologies have emerged in literature, specially concerning the most popular Hill estimator (Hill, 1975). In this work we compare through simulation well-known procedures presented in Drees and Kaufmann (1998), Matthys and Beirlant (2000), Beirlant et al. (2002) and de Sousa and Michailidis (2004), with a heuristic scheme considered in Frahm et al. (2005) within the estimation of a different tail measure but with a similar context. We will see that the new method may be an interesting alternative.

Extreme value Birnbaum-Saunders regression models applied to environmental data

Extreme value models are widely used in different areas. The Birnbaum–Saunders distribution is receiving considerable attention due to its physical arguments and its good properties. We propose a methodology based on extreme value Birnbaum–Saunders regression models, which includes model formulation, estimation, inference and checking. We further conduct a simulation study for evaluating its performance. A statistical analysis with real-world extreme value environmental data using the methodology is provided as illustration.

Gestão de inventários numa empresa de produção de linhas de costura

Dissertação de mestrado integrado em Engenharia e Gestão Industrial

“Learning-by-producing” in the fashion value chain

Proceedings da AUTEX 2015, Bucareste, Roménia.

Otimização das características de um chassis tubular de automóvel de competição com tração a duas rodas motrizes

Dissertação de mestrado integrado em Engenharia Mecânica

Effect of argon ion energy on the performance of silicon nitridemultilayer permeation barriers grown by hot-wire CVD on polymers

One of the authors (S.M.) acknowledges Direction des Relations Extérieures of Ecole Polytechnique for financial support.

Nutritional value, bioactive compounds and antioxidant properties of three edible mushrooms from Poland

Mushrooms contain a multitude of biomolecules with nutritional and/or biological activity. Among the bioactive molecules, phenolic compounds and tocopherols are the most responsible for their antioxidant activity. In the present work, Boletus edulis, Lentinus edodes and Xerocomus badius, three edible mushroom species originated from Poland, were analyzed for their chemical composition and antioxidant activity. Carbohydrates were the most abundant macronutrients, followed by proteins and ash. Fructose, mannitol and trehalose were the prevalent sugars, but glucose was only found in B. edulis. Polyunsaturated fatty acids predominated over mono and saturated fatty acids. Palmitic, oleic and linoleic acids were abundant in the three samples. α- and β- Tocopherols were quantified in all the samples, but γ-tocopherol was only identified in X. badius. Oxalic and fumaric acids were quantified in the three samples; quinic acid was only present in L. edodes, and malic and citric acids were only found in X. badius. p-Hydroxybenzoic, protocatechuic and cinnamic acids were quantified in all the species, while p-coumaric acid was only found in B. edulis. This species and X. badius revealed the highest antioxidant properties, being B. edulis more effective in radicals scavenging activity and reducing power, and X. badius in lipid peroxidation inhibition, which is related with the highest amounts in phenolic compounds and tocopherols, respectively.

Oxygen mass transfer impact on citric acid production by Yarrowia lipolytica from crude glycerol

Production of citric acid from crude glycerol from biodiesel industry, in batch cultures of Yarrowia lipolytica W29 was performed in a lab-scale stirred tank bioreactor in order to assess the effect of oxygen mass transfer rate in this bioprocess. An empirical correlation was proposed to describe oxygen volumetric mass transfer coefficient (kLa) as a function of operating conditions (stirring speed and specific air flow rate) and cellular density. kLa increased according with a power function with specific power input and superficial gas velocity, and slightly decreased with cellular density. The increase of initial kLa from 7 h-1 to 55 h-1 led to 7.8-fold increase of citric acid final concentration. Experiments were also performed at controlled dissolved oxygen (DO) and citric acid concentration increased with DO up to 60% of saturation. Thus, due to the simpler operation setting an optimal kLa than at controlled DO, it can be concluded that kLa is an adequate parameter for the optimization of citric acid production from crude glycerol by Y. lipolytica and to be considered in bioprocess scale-up. Our empirical correlation, considering the operating conditions and cellular density, will be a valid tool for this purpose.

Flow updating: fault-tolerant aggregation for dynamic networks

Documento submetido para revisão pelos pares. A publicar em Journal of Parallel and Distributed Computing. ISSN 0743-7315