Predicting Through Data  Machine Learning VS Statistical Modeling
Belonging to an era which brings a plethora of information available to us, and the amount of work that is being done on the data has been increasing tremendously. This is the basic reason why we need to have a platform where can we can efficiently analyse the data and come up with the solution to our problem statement. This marks the emergence of concepts like Machine Learning and Statistical Modeling.
Machine Learning:
"An algorithm that can assimilate through data without the need of depending on rule based programming."
Machine learning is a branch of artificial intelligence that deals with the idea of learning and acclimatizes through experiences. It grants the feature to a software application to become more explicit and faultless in anticipating the outcome without being explicitly programmed. The primary proposition of machine learning is to form algorithms which can accept input data and analyse it through statistical analysis to predict the possible outcome. As the market of big data is expanding and the amount of data is increasing tremendously, ML as a technology, assists in analyses of these data, helping us in a significant way. Being an automated process it is gaining tremendous prominence and recognition. It is generally applied in the offline training phase. Due to which it has its own share in improving a wide variety of application which ranges from image classification, face detection, anti spam to weather forecasting.
Statistical Modeling:
"Formalization of association within variables in the form of mathematical equations."
Basically, statistical modeling is a mathematically formalized way for approximation and working on the task of predictions through the approximation. The assumptions of the model are described by a set of probability distributions. The core concept deals with the sample, population, hypothesis, etc.
Nowadays, both machine learning which is said to be flexible in nature and statistical techniques are used in pattern recognition, knowledge discovery and data mining. The common objective behind using either of the tools is Learning from Data and analysing the problem. But there are some major differences between the two which distinguishes them from each other 

The difference between both starts from their parents itself, Machine Learning emerges from a branch of Computer Science i.e. AI whereas Statistical Modeling comes from a mathematical background.

ML concentrates on achieving better optimization and execution though statistics works more focusing on inferences.

Statistics has an inclination towards learning about data and to come across a new scientific insight based on the data. Whereas ML deals with solving some complex computational task by allowing the machine to learn about it.

Machine learning does not need any initial assumptions about the variable, all the predictions are done on the basis of input data through the algorithm by recognizing and working on patterns.It is generally applied to a large amount of data to get better and more optimised and accurate results. In contrast to this in the statisticial method, you need to learn about the data and form a hypothesis according to which you plan the proceedings which will lead you to the predictions about the input data. The method is usually favourable for low dimensional data sets.
Both the branches have evolved and improved by learning from each other and will continue to work for the related cause in future. But the reason behind understanding the similarities and knowing their differences helps statisticians and machine learners to enhance and expand their knowledge horizon. It could help in making better decisions along with opening the doors for new inventions.