HitHub — a hit list predictor #Week 2
This week, we discussed with Necva Bölücü(TA of BBM409) and we planned our roadmap and timeline. We have done research about Collaborative Filtering. It is a technique that is used by recommender systems. There are two main concepts using traditional approaches, memory-based, and model-based approaches.
The memory-based approach uses user rating data to compute the similarity between users or items. Typical examples of this approach are neighborhood-based CF and item-based/user-based top-N recommendations.¹
In this approach, models are developed using different data mining, machine learning algorithms to predict users’ rating of unrated items. There are many model-based CF algorithms. Bayesian networks, clustering models, latent semantic models such as singular value decomposition, probabilistic latent semantic analysis, multiple multiplicative factors, latent Dirichlet allocation, and Markov decision process-based models.¹
Deep Learning models provide flexibility of adjustment for their parameters. However, other techniques are based on statistical static routines. Therefore, we have decided to use the Deep Learning approach.
In addition to researches, we discussed the data collecting step. This is the most important part of the HitHub, because we need to select correct songs to get remarkable accuracy of prediction. We have decided to look at each year from 2010.
We will start to create a dataset next week and share the essential Machine Learning algorithms results. After we ensure that we select the correct songs for prediction, we will start to implement the Deep Learning model.
Thanks for reading us. We hope to see you next week!🎧🎧
[1]: Wikipedia. (April 15, 2021). Collaborative Filtering https://en.wikipedia.org/wiki/Collaborative_filtering
