Data mining,machine learning,ai,data science,data science,business Analytics

What is the difference between data Mining (mining), machine learning (learning), and artificial intelligence (AI)? What is the relationship between data science and business Analytics?

Originally I thought there was no need to explain the problem, in the End data Mining (mining), machine learning (machines learning), and artificial intelligence (AI) what is the difference, but a few days ago because of a learning brother asked me, I think I want to find that I can not answer, I looked up the problem on the blog and found that no one had written more detailed and persuasive comparisons and explanations. Then I read the books and papers, and the communication with the tutor, try to say the difference between these, after all, a good definition in the future learning and communication can play a big role. It also complements the relationship between data science and business analysis. Ability is limited, if there is omission, please forgive and correct.

Introduction

This article is divided into two parts, the first part of the data Mining (mining), machine learning (machines learning), and artificial intelligence (AI) the difference between. The difference between the three is mainly the purpose of different, its means (algorithms, models) have a great overlap, so easy to confuse. The second part focuses on the relationship between the above skills and data science, and the relationship between data science and business Analytics. In fact, data scientists themselves are an extension of business analysts in the era of big data.

Data Mining vs. Machine learning vs. Artificial intelligence Data Mining: Schema (pattern) and model for extracting data from existing big data

Keywords: pattern extraction, Big data

Data mining is the mode (pattern) and model of extracting data from existing information (existing information), that is, selecting the most important information for future machine learning and AI data usage. Its core purpose is to find the relationship between data variables. The main reason for its development is the development of big data, the traditional way of data analysis has been incompetent to deal with so many large amounts of seemingly unrelated data processing, so need data mining technology to extract a variety of data and variables of the relationship between, so as to refine the data.
Data mining is essentially a basis for machine learning and artificial intelligence, and his main goal is to extract the superset information from a variety of data sources, and then merge that information into patterns and relationships that you have never thought of. This means that data mining is not a method of proving hypotheses, but a way to construct a variety of hypotheses . Data mining cannot tell you the answers to these questions, he can only tell you that A and B may have related relationships, but it cannot tell you what the relationship between A and B is.
Of course, data mining uses a lot of machine-learning algorithms, but its specific environment and purpose are not the same as machine learning.

machine Learning (Learning): Automatically learns new knowledge from past experience.

Keywords: automation, self-optimization, forecasting, need training data, recommender system

Machine learning is actually a very important part of AI, because at present, in the process of practice, most of the tasks of artificial intelligence processing is actually done in the way of machine learning. Machine learning can be automatically learned with programs and algorithms, and as long as it is designed, the program can be self-optimized. At the same time, machine learning requires a certain number of training datasets (training data set)to build "knowledge" from past experiences.
And the most important function of machine learning in practice is the prediction result. For example, machine learning is over, now there is a new dataset x that needs to be predicted, and the machine learning algorithm will match the learning "knowledge" based on this new data (in fact, knowledge refers to the post-learning mathematical model), and then classify the dataset X into a Class C. More common machine learning, such as Amazon's referral system.

Artificial Intelligence (AI): a broad concept that essentially uses data and models to provide solutions (solutions) for existing problems (existing problems).

Keywords: dealing with problems like people, the collection of technologies

Artificial intelligence is a concept that is relatively different from machine learning and data mining, and the purpose of AI is to create an intelligent computer (which can be assumed to be a robot without knowing how to translate it well). In practice, we hope that this computer can handle a task like an intelligent person . So, in theory, AI includes almost everything and machine-capable content, including data mining and machine learning, as well as the content of monitoring and control processes (Process Control).

What is the relationship between data science and business Analytics?

In fact, we had no data scientist (scientist), and data science, the concept. We call Business Analytics the way we do things.

In 2011,  published the Big data:the next frontier for innovation, competition, and productivity, and now many companies have begun to analyze talent ( Analytical talent) to gain a competitive advantage. Although this is not the first company to come up with this concept, it is the first time that data analysis capabilities help business companies identify potential opportunities, not just for technology companies. Then  argues that by the year 2018, about 190,000 of the projects in the United States lacked " deep analytical Talent", which was driven by Big Data . So far,  has further described "Business Analytics" as "deep analytical capabilities".

Then DJ Patil and Jeff Hammerbacher, in their "Building Data Science Teams", called  "in-depth analysis capabilities" A " database scientist". They mentioned in the text that:

Business analyst seems to be too restrictive, data analyst Anlyst is their competitor, but we still find this term too restrictive. .... We think the best call should be "data scientist", because these people need to use data and science (scientist) to create something new.

Immediately after that, DJ Patil added some key features for finding a data scientist (scientist):

1. Technical Expertise (Technical Expertise): The best data scientists need in-depth expertise in certain scientific disciplines (deep expertise).
2. Curiosity (Curiosity): A good data scientist needs to have a strong curiosity and desire to unearth potential relationships, solve problems and prove hypotheses.
3. the ability to tell stories (storytelling): the ability to use data to tell a vivid story, which makes communication more effective.
4. Smart (cleverness): Ability to creatively solve problems.

Subsequently, the concept of data scientists began to be widely circulated. What are the professional competencies that data scientists need to have? Different companies have different views and opinions (anyway everyone seems to like to put all expectations in a new industry), here is a more popular view:
1.Drew Conway ' s Data scientist Venn Diagram

2.Drew Tierney ' s multi-disciplinary Diagram

3.Gartner

Finally, a "cheat sheet" is included, listing almost all of the business problems, want to get started as a good business analyst, or a data scientist, highly recommended to save!!!!!!!!!!!! When there is time, I will try to translate and explain one after the other.

Expand your Reading (English):

1. What is a data scientist with a unicorn type? : Do not know why now what "unicorn" type of this concept will be so popular, enterprises also love to call Unicorn, the industry also called Unicorn. But why a unicorn, I first thought of the wizard series game. (Cover face ~)

2. Top Data Analytics tools for business: Ten tools for commercial analysis, highly recommended!!!

3. Data science:bridging the Business & IT Gap: The second part of the main source of the original text.

Reference documents:

1. http://stats.stackexchange.com/questions/5026/ What-is-the-difference-between-data-mining-statistics-machine-learning-and-ai
2. http// upfrontanalytics.com/data-mining-vs-artificial-intelligence-vs-machine-learning/
3. https:// Www.researchgate.net/post/What_is_the_difference_between_machine_learning_and_data_mining
4. https:// www.r-bloggers.com/whats-the-difference-between-machine-learning-statistics-and-data-mining/
5. https:// discuss.analyticsvidhya.com/t/ what-is-the-difference-between-machine-learning-data-analysis-data-mining-data-science-and-ai/572
6. http ://www.kdnuggets.com/2014/06/data-science-skills-business-problems.html
7. A variety of messy books and courseware notes.
8. "Building Data science Teams"
9. Big data:the next frontier for innovation, competition, and Productiv ity
10. Drew Conway ' s data scientist Venn Diagram
11. Drew Tierney ' s multi-disciplinary diagram

Category: Data Mining/machine learning

Data mining,machine learning,ai,data science,data science,business Analytics