Exploring Exploration in Recommender Systems: Where? How Much? For Whom?

Recommender systems focus on automatically surfacing suitable items for users from digital collections that are too large for the user to oversee themselves. A considerable body of work exists on surfacing items that match what a user liked in the past; this way, the recommender system will exploit its knowledge of a user's comfort zone. However...

Systematic approaches to music rehearsal segmentation

Practice is always the secret to the success of musicians. Many musicians record their rehearsal sessions and listen back to reflect on their practice. However, the rehearsal sessions are unstructured, messy and rather long compared to commercial recordings. As a result, musicians may not have the capacity to listen back to all of their practice...

Interactive learning for multimedia archive exploration

Recommender systems are essential for filtering immense amounts of available digital content. As these quantities keep increasing, the impact of recommendations does so as well. In this work, we address negative impacts current state-of-the-art recommenders have. For the algorithmic filtering of items that are recommended to users, collaborative...

A behaviour driven recommender system in the fashion domain

Web shops use recommender systems to help users find the products they find interesting in the large amount of available products online. An often used approach to do so is collaborative filtering. This method relies on historical user-item interactions and uses them to recommends products other users found interesting. Fashion is very reliant...

Using Implicit Job Seeker Preferences to Improve Job Recommendation Ranking

This thesis focuses on the field of Job Recommendation. Particularly, we focus on using implicit preferences exhibited by the job seeker in interactions with a web platform to propose an improved ranking algorithm for a job recommendation platform called Magnet.me. We also study evaluation of relevance, and evaluation of recommendation sorting...

Measuring Progress in Music Rehearsals

Practice is an essential part of learning and performing a piece of music. The goal of this thesis is to develop a system for analysing audio recordings of music rehearsals that aids the musician in their studies. We gather audio recordings of rehearsals from pianists and develop two key measures based on these recordings: 1. match distribution,...

Perfect Comps: Identifying Comparable Real Estate Properties using Machine Learning

For traditional, manual real estate appraisals, the appraiser is required to provide a number of comparable properties (the 'Comps'). These comps act as a benchmark for the valuation as well as a provider of context in the final appraisal report. Traditionally, these comps are selected manually by an appraiser based on recent transactions within...

Features for instrument recognition in polyphonic mixes

Automated instrument recognition is necessary to efficiently obtain instrumentation information for the existing large collections of digital music. While automated instrument recognition is possible with very high accuracy for monophonic fragments, the problem has not yet been solved for polyphonic mixes.In this work a system is designed for...

Layered Regression Analysis on Multimodal Approach for Personality and Job Candidacy Prediction and Explanation

Video blogs (vlogs) are a popular media form for people to present themselves. In case a vlogger would be a job candidate, vlog content can be useful for automatically assessing the candidate's traits, as well as potential interviewability. Using a dataset from the CVPR ChaLearn competition, we build a model predicting Big Five personality trait...

Towards Automatic Reverb Addition for Production Oriented Multi-Track Audio Mixing

Sound spatialization is a natural, intuitive but sparsely researched topic in multi-track audio mixing. Although a lot of research has been devoted to the automatic fader gain settings, addition of dynamic range equalization and related effects, delay and Reverb have taken a backseat. The dichotomy in the artistic and engineering approaches to...

Sense Umbrella Connection and Desensitisation: Weather Witness

As of this moment there is a lack of data about rainfall in cities. To collect such data, IBM has started the Sense Umbrella Connection and Desensitisation project. For this project an umbrella was equipped with a piezoelectric sensor and a Bluetooth device to record the rain that falls on the surface of this umbrella. One downside of this...

Automating Valuations for Real-Estate

As GeoPhy is developing its business model and looking into the future of automated valu- ation models (AVM), this project delivers a proof of concept of a system that automates the training, maintaining, and delivery of machine learning models for automated valuations. In order to achieve this goal, the situation and problem were first analysed...