Two data-driven and statistically-oriented attribution models of an advertising campaign of a “Fortune 500 Automobile Manufacturer” are developed.

A comprehensive model is developed in order to predict local box-office receipts of any movie screened in the U.S. prior to its official released date using open data sources.

Different CNNs for the hand-written single-digit image recognition problem of the MNIST dataset are developed, while additional data augmentation techniques take place.

A spatial panel autoregressive model with fixed effects is developed in order to assess the effectiveness of different marketing activities of a fast-food retail chain.

At this project a dataset from NCAA is analysed in order to identify the features that drive a basketball team’s performance.

At this project the daily lettuce demand of a fast-food restaurant chain is forecasted, based on different Exponential Smoothing and ARIMA models.