In addition to insurance companies, pension funds, cooperative banks, investment companies, investment and share funds, and leasing companies, banks represent the most important segment of the financial sector with a stake of nearly 80% of total assets. The balance sum of the banking sector of the Czech Republic amounted to 5,476 billion CZK as of 1.3.2015. Innovative, low-cost players have become the latest trend on the banking market, presenting an alternative to traditional banking. They enforce a business mode of retail banking based on an internet platform. This paper defines and evaluates their activities compared to transnational companies in terms of business success and clients´ perception.

The internet has enabled a fundamental change in consumer behaviour and their understanding of e-commerce business. The main objective of the following article is to present the latest trends in the way of client segmentation associated with individual credit evaluation based on machine learning. The first part discusses the current situation and innovations in the way people pay in an omnichannel world. We describe how the absence of physical money has affected society, how it has changed customer purchasing behaviour, and what this change means for the digital economy and marketing. In the background of the rapid development of big data and the Internet technology, the traditional personal credit evaluation method of the commercial bank faces a significant challenge in the evaluation of personal credit. Based on the limitation of the existing personal credit evaluation method, the second part discusses the necessity of the research on the personal credit evaluation based on the machine learning method and then probes into the comprehensive personal credit evaluation dimension and the advanced data acquisition method of the Internet finance company. And then, the data desensitisation and LOF test were carried out by dynamic desensitisation technique. The abnormal value of the tested data and the random forest method supplement the missing value of the data. The importance index is screened by the gradient boosting decision tree method, and the personal credit evaluation score is output through the scorecard model based on logical regression. After that, the model is tested by BP neural network, and the personal credit level is predicted. The personal credit level fosters customer market segmentation.