O nline Display Advertising's importance as a marketing channel is partially due to its ability to attribute conversions to campaigns. Current industry practice to measure ad effectiveness is to run randomized experiments using placebo ads, assuming external validity for future exposures. We identify two different effects, i.e., a strategic effect of the campaign presence in marketplaces, and a selection effect due to user targeting; these are confounded in current practices. We propose two novel randomized designs to: (1) estimate the overall campaign attribution without placebo ads, (2) disaggregate the campaign presence and ad effects. Using the Potential Outcomes Causal Model, we address the selection effect by estimating the probability of selecting influenceable users. We show the ex-ante value of continuing evaluation to enhance the user selection for ad exposure mid-flight. We analyze two performance-based (CPA) and one Cost-Per-Impression (CPM) campaigns with 20 million users each. We estimate a negative CPM campaign presence effect due to cross product spillovers. Experimental evidence suggests that CPA campaigns incentivize selection of converting users regardless of the ad, up to 96% more than CPM campaigns, thus challenging the standard practice of targeting most likely converting users.

No abstract

In this paper we present a novel framework for classification of the different kind of tissues in intravascular ultrasound (IVUS) data. We expose a normalized reconstruction of the IVUS images from radio frequency (RF) signals, and the use of these signals for classification. The reconstructed data is described in terms of texture based features and feeds an ECOC-Adaboost learning process. In the same manner, the RF signals are characterize using Autoregressive models, and classified with a similar learning process. A comparison is performed among these techniques and with DICOM based classification ones obtaining very promising results.

Coronary plaque rupture is one of the principal causes of sudden death in western societies. Reliable diagnostic of the different plaque types are of great interest for the medical community the predicting their evolution and applying an effective treatment. To achieve this, a tissue classification must be performed. Intravascular Ultrasound (IVUS) represents a technique to explore the vessel walls and to observe its histological properties. In this paper, a method to reconstruct IVUS images from the raw Radio Frequency (RF) data coming from ultrasound catheter is proposed. This framework offers a normalization scheme to compare accurately different patient studies. The automatic tissue classification is based on texture analysis and Adapting Boosting (Adaboost) learning technique combined with Error Correcting Output Codes (ECOC). In this study, 9 in-vivo cases are reconstructed with 7 different parameter set. This method improves the classification rate based on images, yielding a 91% of well-detected tissue using the best parameter set. It also reduces the inter-patient variability compared with the analysis of DICOM images, which are obtained from the commercial equipment.

A main issue in the automatic analysis of Intravascular Ultrasound (IVUS) images is the presence of periodic changes provoked by heart motion during the cardiac cycle. Although the Electrocardiogram (ECG) signal can be used to gate the sequence, few IVUS systems incorporate the ECG-gating option, and the synchronization between them implies several issues. In this paper, we present a fast and robust method to assign a phase in the cardiac cycle to each image in the sequence directly from in vivo clinical IVUS sequences. It is based on the assumption that the vessel wall is significantly brighter than the blood in each IVUS beam. To guarantee stability in this assumption, we use normalized reconstructed images. Then, the wall boundary is extracted for all the radial beams in the sequence and a matrix with these positions is formed. This matrix is filtered using a bank of 1-D Gabor filters centered at the predominant frequency of a given number of windows in the sequence. After filtering, we combine the responses to obtain a unique phase within the cardiac cycle for each image. For this study, we gate the sequence to make the sequence comparable with other ones of the same patient. The method is tested with 12 pullbacks of real patients and 15 synthetic tests.