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.

On the length of bank-firm relationships: an empirical application to a major French bank

NIPE - WP 01/ 2016

Dynamic modelling and analysis of hydraulic forces in radial blood pumps

Dissertação de mestrado integrado em Biomedical Engineering Biomaterials, Biomechanics and Rehabilitation

A spectrophotometry based blood typing device

Blood typing is a crucial step before any blood transfusion. However, sometimes in emergency situations there is no time to determine the blood of the patient beforehand. In this cases, O negative blood type is administered, which has a lesser incompatibility risk to the patient. Nowadays, the “gold standard” blood typing devices cannot be used in emergency situations due to their high response time (about 30 minutes). This paper reports a blood typing device that determines the ABO and Rh human phenotypes. This device is fast (response time – 5 min), low-cost, and portable. Characteristics that make it suitable to be used in emergency situations, contributing to a higher efficiency and quality in healthcare.

An epidemiological study determining blood pressure in a Portuguese cohort: the Guimaraes/Vizela study

Surveying the evolution of blood pressure (BP) levels and hypertension (HTN) prevalence is important. A stringent strategy was utilized in a population cohort study. The BP was measured at two visits at least 3 months apart, and the results were analyzed using the following two methods: the Surveillance method (three BP measurements were performed in one visit, and the results were compared with those published previously for the identical method) and the Clinical method (three measurements per visit for two visits, and the concordant results in both visits were used to determine the BP classification). A total of 2542 subjects completed the evaluation. Using the Clinical method, an average systolic/diastolic BP value of 129.8/76.8?mm?Hg was obtained, and the prevalence of HTN was 31.6%. Of the hypertensive patients, 74.3% were aware of his/her condition; 69.1% were treated and 40.8% of those treated had adequate BP control. A total of 24.7% of subjects changed his/her BP classification between visits, and 13.7% misreported HTN. Using the Surveillance method, we determined that the average global SBP has been maintained, with HTN prevalence increasing in this region, drifting from reported trends nationally and worldwide. There has been improvement in the proportion of treated and controlled subjects; however, the Surveillance method overestimated the HTN prevalence and underestimated the proportion of treated and controlled subjects. The BP levels were higher than observed worldwide in high-cardiovascular (CV) risk countries as well as higher than the minimum risk exposure level for developing CV disease.

Promising blood-derived biomarkers for estimation of the postmortem interval

A precise estimation of the postmortem interval (PMI) is one of the most important topics in forensic pathology. However, the PMI estimation is based mainly on the visual observation of cadaverous pheno- mena (e.g. algor, livor and rigor mortis) and on alternative methods such as thanatochemistry that remain relatively imprecise. The aim of this in vitro study was to evaluate the kinetic alterations of several bio- chemical parameters (i.e. proteins, enzymes, substrates, electrolytes and lipids) during putrefaction of human blood. For this purpose, we performed kinetic biochemical analysis during a 264 hour period. The results showed a significant linear correlation between total and direct bilirubin, urea, uric acid, transferrin, immunoglobulin M (IgM), creatine kinase (CK), aspartate transaminase (AST), calcium and iron with the time of blood putrefaction. These parameters allowed us to develop two mathematical models that may have predictive values and become important complementary tools of traditional methods to achieve a more accurate PMI estimation

Real-Time decision support using data mining to predict blood pressure critical events in intensive medicine patients

Patient blood pressure is an important vital signal to the physicians take a decision and to better understand the patient condition. In Intensive Care Units is possible monitoring the blood pressure due the fact of the patient being in continuous monitoring through bedside monitors and the use of sensors. The intensivist only have access to vital signs values when they look to the monitor or consult the values hourly collected. Most important is the sequence of the values collected, i.e., a set of highest or lowest values can signify a critical event and bring future complications to a patient as is Hypotension or Hypertension. This complications can leverage a set of dangerous diseases and side-effects. The main goal of this work is to predict the probability of a patient has a blood pressure critical event in the next hours by combining a set of patient data collected in real-time and using Data Mining classification techniques. As output the models indicate the probability (%) of a patient has a Blood Pressure Critical Event in the next hour. The achieved results showed to be very promising, presenting sensitivity around of 95%.

Determination of the importance of iron acquisition for Staphylococcus epidermidis biofilm survival in human blood

Dissertação de mestrado em Bioengenharia