Tiago Pereira

Tiago Pereira

Software Engineer

Personal Profile

My name is Tiago Pereira and I'm from Gondomar.

I used to practice a lot of sport but then I took an arrow to the knee. I still try to play whenever I get the chance to go with some friends. I enjoy play video games, although not being very good at it, but they are a way to relax and unwind after a week of work (when I have time that is).

I like to go out at night to a quiet bar or have dinner with friends. I have very different tastes in music and I also love to travel, the world has more to offer than just programming.

I consider myself a well presented, dynamic, motivated, highly committed, responsible and organized person, with entrepreneurial and communication skills able to establish good interpersonal relationships.

Work Experience


Jan 2014 - Present

Android developer

Development and maintenance of Vodafone Cloud.

Development of the new integrated backup solution Vodafone Backup+


Oct 2013 - Jan 2014

Android developer

Development of the Android app Agenda Jurídica, which can be found on Google Play.


Oct 2013 - Jan 2014

Master Thesis in Informatics and Computing Engineering.

Development of a web application for automatic selection of data mining algorithms for new problemsThe technologies used were Ruby on Rails, MySQL, R and Java.


Jun 2013 - August 2013

Android developer

Developed an Android POC to present at the websummit of 2013.

Jun 2012 - August 2012

Mobile engineer

I helped develop the tymr API, implement security with OAuth2 (Draft 20).



A Web2Py library for OAuth2 (draft 20) server [+link].


Developed in Prolog, Agon (or Queen's Guards, Royal Guards) is a strategy game for two players, played on a 6×6×6 hexagonal game-board.

Mars Exploration

Developed in the Repast framework, Mars Exploration is a multi-agent system that simulates an unknown environment, where different agents with different tasks and jobs, have the final goal of exploring and exploiting a specific area.


An Android app, to manage events from Eventful. Extra featured were added were the app would link with the users twitter account informing the events he will be attending, and also showing the weather near the location of an event.


A platform (accessible from FEUPNET) intended to be a low-cost market place, where you can buy and sell digital services with a fixed price of 6€. Web and Android applications were developed.


Rate My School is a web platform (accessible from FEUPNET) that allows students, professors, institutions and companies to rate and be rated, as well as trading comments between them.



A web application for the automatic selection of data mining algorithms for new problems

Advisor: Carlos Manuel Milheiro de Oliveira Pinto Soares [web]

Co-Advisor: Pavel Bernard Brazdil [web]

The interest in the area of classification and prediction is growing rapidly in industry and commerce. A large number of data mining tools are already available. However, such tools are still of limited use to end-users who are not experts. This is due to the fact that machine learning algorithms are non-trivial. As a result, users of machine learning/data mining systems are faced with two major problems: selecting the most suitable algorithm to use on a given dataset, and combining this algorithm with useful and effective transformations of the data. Traditionally, these problems are solved by trial-and-error or consulting experts. The first solution is time consuming and unreliable, while the second is expensive and based on preferences of the experts. Clearly, neither solution is completely satisfactory for the non-expert end-users. Therefore automatic and systematic guidance is required.

By analysing the state of the art we can see how different attempts have been made to address this problem. Some examples are StatLog, ML Toolbox, METAL and DM Advisor, to name a few. Although some of them have shown very interesting results, they are still tool restricted and present a lack of satisfactory user guidance, simplicity and process transparency. In DM Advisor, two of the main shortcomings are the systems scalability and the project did not took full advantage of its distributed approach.

The focus of this dissertation is to improve support to machine learning/data mining end-users, by creating a new system that will allow the recommendation and use of the most promising algorithms in a distributed and collaborative way. This thesis will integrate DM Advisor with OpenML, by collecting its most significant meta-features and applying a meta-learning technique to learn from the collected experiments. The distributed concept introduced by DM Advisor will also be rebuild to take fully advantage of the distributed execution strategy. Finally, the developed system will also have the ability of sharing data with others through OpenML.


Key Skills

  • Android
  • Git
  • Java
  • JSon
  • SQL
  • SVN
  • XML