The same Question was already discussed on research gate, please follow the below link

https://www.researchgate.net/post/What_is_the_difference_between_machine_learning_and_data_mining

"The goal of machine learning is to develop methods that can automatically detect patterns in data, and then to use the uncovered patterns to predict future data or other outcomes of interest. Machine learning is thus closely related to the fields of statistics and data mining, but differs slightly in terms of its emphasis and terminology."

"This is typical of the difference between data mining and machine learning: in data mining, there is more emphasis on interpretable models, whereas in machine learning, there is more emphasis on accurate models"

K. P. Murphy Machine Learning - A Probabilistic Perspective. MIT Press

Dear Vinod Kumar Chauhan

As mentioned by Anita Tripathi, this question almost the same wording was already discussed by another group of researchers. The link is right, personally already explored and responses are very interesting.

Practically I almost agree with the answers. The consensus reached in the other group, primarily consisting of researchers with expertise in statistics, information systems and computer experts and artificial intelligence, consider data mining and machine learning are identical or similar.

However, a smaller group of this discussion group and who participate at this time, we think that there are differences, mainly from the theoretical-conceptual and personal experiences of everyday life view, and Human Learning is very different the Machine Learning (Automatic learning)

I think that differences persist when considering deep human interaction with the machine. That is, the communication process established between human intelligence to investigate, understand, interpret and generate knowledge using algorithms and programming language called "Artificial Intelligence"

Let's look in more detail as understood and helps each of these methods and tools for computing, Data Mining, Artificial Intelligence and Automatic Learning ,

The term Data Mining, becomes metaphorically Mining, it understood as the "mining industry valuable to humans and found deep in the earth products" Extrapolating this knowledge and relate the field of information and computer science, then we will understand that data mining means looking "veins" of information. In this metaphor, it would be looking at the grain of the valuable information that exists in the Databases and Knowledge.

In other words, Data Mining is the strategy and method for discovering new knowledge within a dataset unexplored. In the field of information technology, also it refers to the process of identifying "Patterns and Models" in large volumes of information or data set.

At this point in the discussion it is fair to say that the most effective Data Mining is to be performed with tools developed through algorithms and programming of Artificial Intelligence (AI). In turn, the Data Mining methods are: a) Artificial intelligence; b) The Automatic Learning; c) Statistics; d) Database.

Taking up one of the methods of Data Mining (MD), Automatic Learning (AL), this means that the machine learns from experience in the use and application of the best tools of AI for this activity (MD )

But we did not go any further without pretending cosificar Automatic Learning but not humanize, this is a breakthrough, but again reached the point where the micro-computer for faster and more powerful it and fed by an AI program for properly process information, give us answers according to how it was programmed by us humans, but it (the machine software and hardware environment) "will not be aware that learns" the processing of this information .

On the other hand, we get the ideal and enough information to seemingly "communicate and talk to a micro-computer" fed programs and algorithms as robust as those in the IA us, almost as if we did to another human being, but the man with whom we would communicate would be virtually to ourselves, asking and responding to us in a mirror, almost like a psychotherapeutic interview.

Finally, some thoughts:

• Human interaction with AI as feeding large servers and search engines on the Internet, are able to respond "intelligently" to the extent that they are asked in the same way, that is, making intelligent questions.
• Using the methodology of the Evidence-Based Medicine (EBM) in learning and problem solving; for example, a doctor can make an intelligent question on web sites or search engines browsers and get information from different databases and knowledge and find new relationships (eg Google.).
• Also, if the question is done intelligently, with binding conditions as "Y (Yes) vs O (No)" which in the form of Venn diagrams (information fields and fields of knowledge) when inter-acting or overlap , could generate new sources of information and new knowledge (original knowledge).

Finally, the generation of new sources of information are combined machines without realizing they are doing original overlapping and are producing new knowledge. In other words, this is Automatic Learning, but ....... without self-knowledge or awareness of the machine, but of great value and utility to the human who has learned to use these tools.

Attached is a publication that exemplifies this automatic generation of original knowledge.

Cheers

Sincerely

Dr. Jose Luis Garcia Vigil

Good contributions from all.

Just to add a few lines.

Data mining focuses on exploration of data to find patterns and trends. The outcomes and data questions are not fixed because the operator/user is human itself; it could vary based on the user requirements. The focal point in data mining is to generate new information from data sets.

On the other side, machine learning gives computers the ability to learn without being explicitly programmed; machine learning look into specific scenario where the data questions are fixed and the outcome is generated through systematic methods. Similarly, the machine learning is a very generalised form of AI while data mining is more specific. 

I guess a lot could be said on the above; good luck. 

Machine Learning relates with the study, design and development of the algorithms that give computers the capability to learn without being explicitly programmed.

Data Mining can be defined as the process that starting from apparently unstructured data tries to extract knowledge and/or unknown interesting patterns. During this process machine Learning algorithms are used.

So as per my views both things can be used as counterparts of each other. More details can be found on:

http://www.sas.com/en_us/insights/analytics/machine-learning.html.

http://www.sas.com/en_us/insights/analytics/machine-learning.html

Iinteresting contributions

With similar arguments, my previous contribution specifies that Data Mining (DM) is a strategy and method for discovering new information and new knowledge of databases not previously explored. It also allows to recognize "Models and Patterns" of information.

For its part, Automatic Learning (AL) in turn is strategy and method of the MD using automated algorithms and iterative learning patterns in the data. In other words and as I mentioned earlier, the AL focuses on mathematical algorithms that learn from data with minimal or no human intervention.

Of course all this happens in the field of computer awareness or researcher using these automated tools, and learn about the process, the best use of them, which does not happen with the machine, since it is not self- aware of "what you learn." This is the crux of the matter and an important part of differentiation is sought with the question that started this discussion.

My two cents!!

Often data sources for data mining are incidental. Data are typically operational data like market basket, call detail records in telecom industry, insurance claims, astronomy observations,  etc.. Patterns mined from these data provide insights into operations/causal factors. Questions raised in data mining are relatively unstructured. 

Machine learning in my opinion is relatively more goal oriented. Most important task is prediction i.e. supervised learning or developing a predictive model. Data are generated with the specific question/goal in mind. Features are suitably constructed/extracted to answer the specific question. Eg, learning the characteristics of carcinogenic cells, characteristic of loan defaulters,  etc..  

Data mining and machine learning are not the same.

Data is utmost important in this knowledge era. Machine learning algorithms and techniques are used to explore previously known and unknown(hidden) information in a large dataset/database. This unknown information can then be assimilated in to knowledge for a particular domain (e.g business). Further, this knowledge is formulated as a rule to improve sales. 

Please go through AI and Machine learning, supervised, unsupervised, reinforced learning...etc.   You will get an concrete idea..

Sivagaminathan P G