Mobile Network trafficprediction : Based on machine learning

Abstract: The investing market can be a cold ruthless placefor the layman. In order to get the chance of making money inthis business one must place countless hours on research, withmany different parameters to handle in order to reach success.To reduce the risk, one must look to many different companiesoperating in multiple fields and industries. In other words, it canbe a hard task to manage this feat.With modern technology, there is now lots of potential tohandle this tedious analysis autonomously using machine learningand clever algorithms. With this approach, the amount ofanalyzes is only limited by the capacity of the computer. Resultingin a number far greater than if done by hand.This study aims at exploring the possibilities to modify andimplement efficient algorithms in the field of finance. The studyutilizes the power of kernel methods in order to algorithmicallyanalyze the patterns found in financial data efficiently. Bycombining the powerful tools of change point detection andnonlinear regression the computer can classify the differenttrends and moods in the market.The study culminates to a tool for analyzing data from thestock market in a way that minimizes the influence from shortspikes and drops, and instead is influenced by the underlying pattern.But also, an additional tool for predicting future movementsin the price.