During this week we will continue to process the data and test our models with the various differences. We are, at this point, organizing all the code developed, including everything that, in our view, was relevant to the development of the project in a single… Ler mais »7th Week Report
This week we knew we had work to do. We have submitted the State of Art part of the article last weekend, as well as the “Methods used” topic so we can have feedback from the teachers regarding this topic. For this week, we continued… Ler mais »6th Week Report
On the first day of practical classes, we continued to perform the exercises that were available for us, using our dataset. After some tests and conversations with the professor, we came to the conclusion that splitting the dataset into 50/50 (half toxic questions and the… Ler mais »5th Week Report
At the start of this week, we had our first issue. Our dataset had so many unique values, around 1.3 million, that we weren’t able to run and test the pre-processing code as it takes hours to run everything. So we had to down-sample the… Ler mais »4th Week Report
This week we had the introduction to the two curricular units.It was good for us to understand the next steps to follow and what types of material we are going to take. We also were presented to the third challenge guidelines and evaluations methodologies which… Ler mais »1st Week Report
Earlier this week we had a masterclass on Real-Time Data Mining with Professor João Gama, which was very enriching to know a little more about the topic and what we are and will learn. In practical classes, we decided to review the following topic.As for… Ler mais »3rd Week Report
In this first week, we started by discussing which theme to follow in the area of music. This theme will have to be framed with both curricular units, that is, it will have to apply neural networks and it will also have to have natural… Ler mais »2nd Week Report
Toxic content on social media is a growing problem that affects platforms and the people using them. Quora is one of those platforms, that took the initiative to create a challenge on Kaggle related to this problem, with the name of “Quora Insincere Questions Classification”,… Ler mais »Description
The challenge aim to solve the problem of predicting if a song will become a Billboard hit and build playlists around it using AI. The used dataset has almost 18 000 songs and was retrieved from Kaggle, which supports a variety of datasets publications formats.… Ler mais »Description
The challenge aims to expose techniques and intelligent systems that support the definition of vehicle characteristics suitable for the user profile in online platforms. Despite all the features on car ecommerce sites, many users find it difficult to find the ideal car that best suits… Ler mais »Description