A Novel Recommendation System for Next Feature in Software
Software that needs to fulfill many tasks requires a large number of components. Users of these software need a lot of time to find the desired functionality or follow a particular workflow. Recommendation systems can optimize a user’s working time by recommending the next features he/she needs. Given that, we evaluate the use of three algorithms (Markov Chain, IndRNN, and LSTM) commonly applied in sequence recommendation/classification in a dataset that reflects the use of the accounting software from Fortes Tecnologia. We analyze the results under two aspects: accuracy for top-5 recommendations and training time. The results show that the IndRNN achieved the highest accuracy, while the Markov Chain reached the lowest training time.
KeywordsRecommendation system Independently Recurrent Neural Network Sequential recommendation Deep learning Commercial applications
This study was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior – Brasil (CAPES) – Finance Code 001. The authors also thank the Fundação Cearense de Apoio ao Desenvolvimento Científico e Tecnológico (FUNCAP), for the financial support.
- 1.Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). https://www.tensorflow.org/
- 2.Chollet, F., et al.: Keras (2015). https://keras.io
- 4.He, Q., et al.: Web query recommendation via sequential query prediction. In: IEEE 25th International Conference on Data Engineering, pp. 1443–1454 (2009)Google Scholar
- 5.Hidasi, B., Karatzoglou, A., Baltrunas, L., Tikk, D.: Session-based recommendations with recurrent neural networks. CoRR 1511.06939 (2015)Google Scholar
- 7.Hosseinzadeh Aghdam, M., Hariri, N., Mobasher, B., Burke, R.: Adapting recommendations to contextual changes using hierarchical hidden Markov models. In: Proceedings of the 9th ACM Conference on Recommender Systems, RecSys 2015, pp. 241–244 (2015)Google Scholar
- 8.Jannach, D., Ludewig, M.: When recurrent neural networks meet the neighborhood for session-based recommendation. In: Proceedings of the Eleventh ACM Conference on Recommender Systems, RecSys 2017, pp. 306–310 (2017)Google Scholar
- 9.Li, S., Li, W., Cook, C., Zhu, C., Gao, Y.: Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN. arXiv e-prints arXiv:1803.04831, March 2018
- 10.Quadrana, M., Cremonesi, P., Jannach, D.: Sequence-aware recommender systems. CoRR 1802.08452 (2018)Google Scholar
- 12.Soh, H., Sanner, S., White, M., Jamieson, G.: Deep sequential recommendation for personalized adaptive user interfaces. In: Proceedings of the 22nd International Conference on Intelligent User Interfaces, pp. 13–16. ACM IUI (2017)Google Scholar
- 14.Zhang, Y., et al.: Sequential click prediction for sponsored search with recurrent neural networks. In: Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2014, pp. 1369–1375 (2014)Google Scholar