Data Analysis and the Future of Data Analytics.

What is Data?

Data: Data is any facts and figures collected from various sources.

Data can be raw, difficult to analyze, it can be unstructured and lack format.

What is Data Analysis?

Data Analysis: Data Analysis is the process of using the data by converting it into useful information.

The data is given a meaningful structure and format and is entered into databases, data warehouses, cloud-based programs before doing various kinds of analysis.

Note:

·       Missing data should be addressed, or a method should be used in place to use the missing values. A numeric non-applicable value or code can be used to substitute the missing value.

·       The data can be transformed using business rules into values that can be used for Data Analysis.

·       Data is also identified to establish relationships with other data and used for modeling.

·       Data Analysis can be done to form a hypothesis and use our domain knowledge to predict the behavior of data. Another method is to use mathematical models and statistics to confirm the hypothesis.

Types of Data Analysis:

There are mainly 8 types of data analysis methods.

·       Descriptive Analysis: The Descriptive Analysis is used to summarize a given data set. It looks at the properties of one or more variables.

The statistical techniques used are:

1.Frequency Distribution: To determine all possible values of a variable or the number of times the variable appeared in the given data set.

2.Central Tendency Measures: To calculate the central tendencies like the Mean (mean is the average of the values), Median (middle value of the data set), Mode (is the most frequently occurring value).

3.Dispersion: To calculate the range variance and Standard Deviation (square root of the variance) to see the spreading of variables around the central tendency.

·       Diagnostic Analysis: The Diagnostic Analysis is involved in identifying certain patterns in the data, analyzing other related sources, to understand current data trends and differences.

·       Exploratory Analysis: The Exploratory Analysis helps in discovering connections, patterns, and relationships between the variables in the data. It is useful in understanding the relations and forming hypotheses to collect data.

·       Inferential Analysis: The Inferential Analysis is about estimating using a sample from the population. The most used statistical methods are the T-Tests and Variance Analysis.

·       Predictive Analysis: Predictive Analysis uses current or past data to make predictions about the future. This analysis is mainly dependent on the variables used. A simple linear model may work in some cases whereas a complex model needs fine tuning of some variables.

·       Causal Analysis: This analysis helps in identifying the effect of change in one variable with another variable. It is mostly based on assumptions.

·       Mechanistic Analysis: This analysis is conducted with controlling variables needing high accuracy with almost no error. It is applied in engineering or biological behavior processes.

·       Prescriptive Analysis: This analysis involves combining other analysis data. It is applied after Predictive Analysis and determines the actions to be taken according to the predicted trends within the variable constraints.

What is Data Analytics?

Data Analytics uses facts, numbers and dates to organizes data so that, the business can analyze the data and make better decisions. It involves cleaning, transforming and modeling data to build insights and support business strategies.

What is Cloud Computing?

Cloud Computing: Cloud computing provides computing resources accessible on demand. Cloud Computing technologies provide cloud resources and various analytical tools to work on complex business data using algorithms.

Cloud analytics: Cloud analytics provide scalable resources for data analytics use cases, reporting and for predictive analytics dashboards. They provide data encryption, easy access and security.

Cloud analytics include Data Sources, Data Models, data warehousing and computing resources.

Types of Cloud Analytics:

Public Cloud: Organizations accessing Public Cloud analytics share the same resources and services without sharing data.

Private Cloud: Private Cloud analytics are accessed fully by one organization only, but it is expensive.

Hybrid Cloud: Hybrid Cloud analytics offer both public and private analytics access for an organization.

The future of Data Analytics:

Data Analytics tools generate Dashboards based on predefined filters. This helps in reviewing key metrics to make informed decisions.

Both cloud computing and data analytics help businesses make faster decisions and improve efficiency.

Generative AI: Generative AI creates new content based on the prompt provided to it.

It is a type of Artificial Intelligence that uses neural network and deep learning algorithms. The knowledge for the algorithms comes from a large source of data that was fed to using the neural networks. These algorithms are used to identify patterns using the existing knowledge and create new content.

These AI algorithms can create new original text, images, audio, video and any other content as instructed in the prompt using a natural language.

Ex. Siri and Alexa are AI bots that use Natural Language Processing (NLP) techniques that interpret the meaning and provide response in human understandable form.

The human language is generated using Large Language Models (LLMs). These are advanced AI systems designed to understand human language and generate intelligent responses.

Using deep learning models generate responses based on books, websites and text based articles from publicly available sources.

LLMs can be used for new content generation and logical reasoning, summarizing and searching.

Ex. Generative AI can help with explaining how clean data using Power BI.

Agentic AI allows to make automated decisions using Dashboards and by initiating workflows based on the governance rules. It can plan multiple steps and decide what to do next.

Ex. Agentic AI will help with the steps to do a process and notify after it is done.

Load the dataset

Clean and validate the fields

Create measurable KPI's

Build visualizations and

Notify or Log results.

Examples of some AI automation tools for Data Analytics:

Graphy.app – creates graphs and interactive charts.

Manus.im -converts data set into a report based on a prompt.

Julius.ai – uses generative AI for data analysis and creates workflows.