**What is data science?**

Data science is the study and analysis of data using statistical, computer and mathematical methods to obtain new knowledge and information from data. This science includes processes such as collecting, storing, processing and analyzing data using various tools. Data science is a combination of mathematics, statistics, computer engineering, artificial intelligence and related subjects. Using these methods, one can look for patterns, relationships and meaning in data and seek to improve decisions and make better predictions in various fields such as social sciences, life sciences, finance, etc.

Data science has had a great impact on different societies and is currently used in many industrial and non-industrial fields. For example, in medical sciences, data science can be used to analyze medical data and improve the diagnosis and treatment of diseases. Also, in industry, data science can be used to improve the performance of production processes, marketing and human resource management. In general, data science allows us to use the data available in societies and industries to improve performance and increase efficiency in various fields.

**Descriptive analysis**

Descriptive analysis is a statistical method in which data collected from a sample is used to describe and summarize that data. In this method, the data are analyzed numerically or non-numerically, and the mean, median, dispersion and frequency of different values can be calculated.

Using descriptive analysis, we can extract important information from the data and display the results graphically or tabularly to gain a better understanding of the data. This method can be used in many different fields, including social sciences, economics, statistics, medicine, psychology, etc.

In general, descriptive analysis provides insight into the past, this statistical technique is descriptive as the name suggests. More specifically, it looks at the data and analyzes past events and situations to give you a general idea about the future. Simply put, it looks at past/historical performance to reveal reasons for past success or failure. The above approach allows us to learn from past behaviors and find out how they may affect future performance.

**Regression analysis**

Regression analysis is a statistical method that allows modeling the relationship between a dependent variable and one or more independent variables. In this method, using the collected data, a model is built to predict a response variable using one or more descriptive variables.

The regression model may be represented in the form of a mathematical relationship or a graphical diagram. In regression models, one of two types of linear regression or non-linear regression is usually used. In linear regression, the descriptive variables are related to the response variable using a straight line, while in nonlinear regression, the relationship between the descriptive variables and the response variable is non-linear.

Regression analysis can be used in many different fields including social sciences, economics, medical sciences, engineering, etc. In data mining, this technique is used to predict values given a specific data set. For example, regression may be used to predict the price of a product given other variables. Regression is one of the most popular data analysis methods used in business, data-driven marketing, financial forecasting, etc.

**Factor Analysis**

Factor analysis is a statistical method used to reduce the number of dependent variables (response variables) in a data set. In this method, we convert several dependent variables into several key factors with the aim of reducing the number of variables. Factors are linearly related to the dependent variables, and each factor usually represents a key feature of the data. In this method, by using the covariance matrix or correlation matrix of the data, we obtain the key factors and can use them to analyze complex data.

Using factor analysis, we can look for hidden patterns in the data, and by analyzing the behavior and relationship between variables, we can obtain patterns that may not be easily observable and explainable, but can provide explanations for interpreting the data. Factor analysis is commonly used in various fields such as psychology, social sciences, medical sciences, etc.

More precisely, factor analysis is a data analysis technique derived from regression that is used to find the underlying structure in a set of variables. The above technique emphasizes finding new independent factors (variables) that describe the patterns and relationships between the main dependent variables. Factor analysis is a very popular solution for researching the relationships of variables and is mainly used in connection with complex topics such as psychological scales and socio-economic status. Factor analysis is an essential step to achieve clustering and classification methods in an efficient manner.

**Scatter analysis**

Dispersion analysis means examining the dispersion of data and the amount of difference between data. In this method, we can use various statistical measures such as variance, standard deviation and coverage to check the dispersion of the data. Variance indicates the amount of dispersion of the data, so that the higher the value of the variance, the more scattered the data. The standard deviation also shows the amount of dispersion of the data, so that the higher the standard deviation, the more scattered the data. Coverage also shows how much data is in a certain range.

Using scatter analysis, we can understand more about a data set and look for hidden patterns in the data. This method can be used in many different fields, including social sciences, medical sciences, economics, etc. In general, scatter analysis is very useful for better understanding the data and finding hidden patterns in the data.

Scatter analysis is not a very common method, but it is used in data mining and some data mining professionals use it. The above technique is used to describe the spread of a set of data. Measuring dispersion helps data scientists study and understand the diversity of subjects. In general, dispersion has two important issues. The first is that it shows the changes between the elements and the second is that it shows the changes around the average value. If the difference between the value and the mean is significant, the dispersion is high, otherwise it is low.

**Diagnostic analysis**

Diagnostic analysis is a statistical method that is used to investigate the causes of problems and disorders in data. In this method, using the collected data, we seek to find the roots of the problems in the data and ways to fix them.

In other words, diagnostic analysis helps us identify problems and deficiencies in data and find ways to fix them. In this method, various statistical criteria such as mean, variance, standard deviation and correlation coefficient are used. Diagnostic analysis is commonly used in various fields such as medical sciences, psychology, economics, etc. Using this method, we can look for solutions to fix problems and improve the data, and thus achieve a more accurate analysis and interpretation of the data.

Diagnostic analysis is one of the most powerful classification techniques in data mining. Diagnostic analysis uses a variable measurement approach on different groups of elements to delineate or, more precisely, demarcate the points that distinguish the groups from each other.

**Time series analysis**

Time Series Analysis means examining changes and time patterns in data. In this method, data is collected and analyzed sequentially over time.

Time series analysis includes many different statistical methods such as ARIMA modeling, spectral analysis, graphical modeling, etc. Using this method, we can identify different temporal patterns in the data and seek to predict future developments.

Time series analysis is commonly used in various fields such as financial management, economics, social sciences, etc. For example, in economic sciences, time series analysis can be used to predict the trend of growth or stagnation in the economy. Overall, time series analysis can help us identify patterns in time data and seek solutions to improve them.

In almost all scientific fields, measurements are made over time. These surveys lead to the production of organized data sets called time series. The most significant example in this field is the daily value of the stock market index. In its simplest definition, time series data analysis is the process of modeling and explaining time-dependent series of data points. The goal is to extract meaningful information from the data.

**Artificial Neural Networks**

It is the most popular and newest method of data analysis. Inspired by biological samples, these networks enable computers to function similar to the brains of humans or other organisms. Artificial neural networks, often called neural networks, are a metaphor for the brain's ability to process information. These computational models are borrowed from biological samples. They consist of an interconnected group of artificial cells and process information using a computational approach.

Neural networks are widely used in data mining. They are well able to accept and process noisy data and their output is very accurate. Neural networks are used in many commercial prediction and classification applications.

**Evolutionary programming**

Evolutionary programming combines different types of data analysis using evolutionary algorithms and is very popular in the world of data mining. Genetic algorithms, genetic programming and evolutionary algorithms are among the most used examples in this field. Today, data management agencies use evolutionary algorithms to overcome the challenges associated with big data. They have the ability to explore large search spaces and discover efficient solutions, are almost insensitive to noise (a problem that machine learning experts face), and can handle interactions between features in an excellent way.

**decision tree**

It is one of the popular and modern classification algorithms in data mining and machine learning. A decision tree is a tree-shaped diagram that represents a classification or regression model. A decision tree divides a data set into smaller and smaller subsets containing samples with similar values, while at the same time a related decision tree is continuously developed. The tree is constructed with the help of branches to show how and why one choice might lead to the next. The operation of decision trees is easy to understand and makes the classification process simple and fast.

Random forest

Well, since the picture above is cloud forests, it is not bad to explain more about the trees!! Decision trees start with a basic question. Should I surf? The story starts from this point, followed by other questions that aim to get an answer to the main question. Will the waves last long? Does the wind blow on the beach? These questions form decision making nodes in the tree and are a solution for dividing data. Each question helps the expert reach a final decision, which is denoted by a leaf node. Observations that match the criteria follow the "yes" branch and observations that do not match the criteria follow the alternative path. Decision trees seek to find the best partition for a subset of data and are usually trained through a classification algorithm and a regression tree. Measures such as Gini impurity, information gain, or mean squared error can be used to assess the quality of the partition.

**Fuzzy Logic**

Fuzzy logic is a mathematical method that is used to model complex systems and make decisions under conditions of uncertainty and ambiguity. In this method, instead of using precise and binary values (0 and 1), fuzzy and ambiguous values (between 0 and 1) are used.

Fuzzy logic allows us to look for better ways to make decisions in situations where the data has ambiguity and uncertainty, using concepts such as "high", "low", "medium", etc. In this method, decisions are made based on fuzzy probabilities and fuzzy values. Fuzzy logic is commonly used in various fields such as robotics, industrial control, artificial intelligence, decision making systems, etc. For example, in robotics, fuzzy logic can be used to decide the robot's direction and speed. In general, fuzzy logic allows us to make better decisions and improve the performance of systems in the face of complex conditions and uncertainty.

Fuzzy logic is used to deal with uncertainty in data mining problems. Fuzzy logic modeling is one of the probability-based data analysis methods and techniques, it is relatively new, but it has a great capacity to extract valuable information from different data sets.