Prioritizing pull requests

Previous work showed that in the pull-based development model integrators face challenges with regard to prioritizing work in the face of multiple concurrent pull requests. We identified the manual prioritization heuristics applied by integrators and extracted features from these heuristics. The features are used to train a machine learning...

Prioritizing and selecting KPIs: An AHP-based model to evaluate the alignments among strategy business model and performance metrics

User-centered Prioritization: A 2-dimension approach for evaluating the user value of backlog topics

User-centered Prioritization is a method for assessing the user value of the different topics present in the product backlog agile software development teams work with. It not only puts the users in the spotlight during this decision-making procedure by basing it on the benefits achieved and the level of fulfilment of user needs, but also...

Identifying the Critical Infrastructure Objects

Maintaining infrastructure asset systems can be challenging for public authorities since we are living in a time where there is an increasing rate of deterioration of infrastructure assets such as tunnels, bridges and streets. This is due to the ageing and the increased use of these assets. As a result, some assets need additional maintenance...

Towards a Governance Structure for the Data-Driven Prioritization of Humanitarian Aid: A data ecosystem approach

The incidence of natural disasters worldwide is increasing. As a result, there is a growing number of people in need, whereas limited resources to help these people are available. It is therefore important to effectively and efficiently prioritize the most vulnerable people in the preparedness phase, and the most affected people in the response...

Airport pavement management decision making: A prioritization tool to select pavement sections requiring M&R treatments

An increase in air traffic demand, aging pavement infrastructure, and limited funds make pavement management decision making a difficult process. Pavement management systems (PMS) are essential for pavement management. PAVER, the most common airport pavement management system (APMS) assists pavement managers by identifying the surface condition...

Prioritized Experience Replay based on the Wasserstein Metric in Deep Reinforcement Learning: The regularizing effect of modelling return distributions

This thesis tests the hypothesis that distributional deep reinforcement learning (RL) algorithms get an increased performance over expectation based deep RL because of the regularizing effect of fitting a more complex model. This hypothesis was tested by comparing two variations of the distributional QR-DQN algorithm combined with prioritized...

Short-term forecasting of non-stationary time series using multiple feature selection methods

Time series forecasting has been proved to be relatively easier for stationary time series, compared to non-stationary time series. This research proposes a method to partially omit the non-stationarity of the data using prioritized sampling. Using multiple feature selection methods in combination with a random forest regressor (RFR), we aim to...

Agent-based Modelling of Complex Socio-technical Operations at Airports Serving as a Humanitarian Hub

Airports play a key role during humanitarian relief operations. It is therefore important to connect the humanitarian and aviation disciplines to find possibilities to improve these airport operations when operating during and after a humanitarian disaster. This research provides a methodology on how to model, verify, calibrate and validate the...

Process Design for Digital Innovation Portfolio Management: Master thesis report

This thesis focuses on designing a process for balancing and prioritizing the digital innovation project portfolio of a rental equipment company. The company operates in a traditional industry in which themes like digital transformation and digitalization are new emerging themes that are yet to be accepted by the industry. Therefore, in order to...

Predictive Test Case Selection and Prioritization at Adyen

The set of regression and integration tests at many modern software companies is huge. It is difficult to run all tests after each code change, so the tests are often run for batches of code changes by different developers, late in the release cycle. This has developers waiting for tests longer than desirable and makes it...

Automating cyber security advisories: Supervised machine learning for automated decision making

There is an everlasting struggle for organisations to remediate vulnerabilities in IT systems before being the victim of an exploitation. Organisations try to reduce this struggle by turning to specialized cyber organisations, which use their expertise to recommend resolving a subset of vulnerabilities. Unfortunately, the process of recommending...

Prioritizing states with action sensitive return in experience replay

Experience replay for off-policy reinforcement learning has been shown to improve sample efficiency and stabilize training. However, typical uniformly sampled replay includes many irrelevant samples for the agent to reach good performance. We introduce Action Sensitive Experience Replay (ASER), a method to prioritize samples in the replay buffer...

Identification and prioritization of factors and their influence on corporate venturing success: The analysis of influential factors affecting the success of the corporate ventures using the Best-Worst methodology and their prioritization assessment

Corporate venturing practices have been one of the most successful practices in terms of shared innovation or leveraging outside talent to further one’s competitive edge in the rapidly growing and evolving industry of technology. Since, technology has been one of the main driving factors in providing solutions for achievement of short term and...

Social Prioritization for the Energy Grid: Energy Justice Evaluation and Impact Analysis

The electricity grid in the Netherlands is highly congested and poses a significant challenge due to increasing demand and the transition to sustainable energy sources, which overwhelms the existing infrastructure. To address this issue, Distribution System Operators (DSOs) like Alliander are tasked with managing waiting lists for power...