Predictions get better with deep learning
By : Flytxt R&D Team
Big Data and Deep Learning are among the biggest trends in the recent years, leading to an upsurge of research, as well as industry and business applications. While Big Data offers great potential in data analytics, harvesting of valuable knowledge from Big Data is not an ordinary task. As the data keeps getting bigger and bigger, deep learning is going to play a key role in providing big data predictive analytics solutions, particularly with the increased processing power and the advances in graphics processors.
In contrast to most conventional machine learning methods, which are considered using shallow-structured learning architectures, deep learning refers to machine learning techniques that use supervised and/or unsupervised strategies to automatically learn hierarchical representations in deep architectures. With the composition of enough such representations, very complex functions can be learned. Deep learning methods are representation-learning methods that allows a machine to be fed with raw data and to automatically discover the representations, thereby eliminating the need for feature engineering which occupies almost 90% of effort in industrial machine learning. Deep Learning has turned out to be very good at discovering intricate structures in high-dimensional data and is therefore applicable to many domains such as in dimensionality reduction, supervised learning, recommender systems, natural language processing, etc.
Flytxt is in a process to incorporate deep learning for its various applications. The churn prediction problem was attempted using deep learning. The dataset involved observations from 0.33 million subscribers of a major telecom service provider. Deep neural network, a popular deep learning architecture, was used for detection. The network can contain a large number of hidden layers consisting of neurons with a variety of activation functions. A superior accuracy of 87.60% and area under the ROC of 91.76% was obtained. It shows that deep learning offers huge potential in such applications.