Showing posts with label data science. Show all posts
Showing posts with label data science. Show all posts

Sunday, 17 July 2022

What is Data Science? - End to End project - part 1

No comments :

 


In this post, we will see how a simple data science project life cycle will be!

Data Science Project Life Cycle

1. Understanding the Business Problem


Without a business requires no project exists. So once the client approached us for a solution. Then we have to understand their business problem and requirements. We have to get clarification of all of your questions and queries initial stage of the project to avoid back and forth.

The client will approach a data science firm which will be mostly a Marketing Research firm or Data Analysis firm.

They will have a kick-off call meeting where they will discuss the business problem statement and their requirements with the technical team and frame the steps to be executed.

After the meeting they will identify the below:

1. Exact Problem statement
2. Where and how to collect data from
3. Budget and Duration of the Project 
4. Required Output files
 

2. Data Collection

Once the problem statement is identified and the data collection process is defined then the project goes live.

Data Collection:

There are various ways to collect data.

1. Survey
2. Telephonic Interview data
3. Data collected from real-time places such as hospitals, clinics, and individual persons.


The data will be collected based on the requirements of the client, they most probably define a questionnaire to collect the data.

Once the data is ready the project will start in terms of technical part.

3. Data Analysis

Data analysis is the major part of a Data Science project. It is also the crucial part of the entire project where all the other projects depend on the data provided by the data analysis team. So it is really very important to work more cautiously when doing the data analysis.

There are different tools to do the data analysis which we will discuss in the upcoming episodes.

During the data analysis process, the team will prepare a cleaned version of data after checking the data quality, genuine form of data and more focus on the valid data.

The team will also build some partial insights with visualization for the client to look at to know that the project is on right track. Also the client can direct the team to focus on a few areas based on the analysis they did so far.

4. Machine Learning Model

Most of the projects can be 90% completed once the Data analysis project is over. Only a few projects need a machine learning model based on the complexity of the data and volume of the data. 

The Machine Learning models will be helpful to automate our work and make the big volume of data analysis in a simple and faster manner. We will learn more about machine learning in upcoming episodes.

5. Insights

Finally, we will get prepared with the insights and output files in the format the client has requested. It can be a simple excel, CSV file, text file, pdf, charts, graphs, slides etc...

There will be a secured mode of communication to deliver the projects.

Based on the client's suggestion there might be some more tune-up in the insights else the project can be sign-off.

Hope this article might be helped you in understanding what a data science project will be like. In upcoming episodes, I will share the tools and technical part of data science. 


Read More

Saturday, 16 July 2022

What is Data Science?

3 comments :


 


Data Science is a combination of multiple disciplines that use statistics, data analysis and machine learning to analyze data and extract knowledge and insights from it.

What is the Use of Data Science?




 Data Science is the art of providing insights based on the provided data from the client or data collected based on the business requirement.

That Insight will be the output of a data science project where it will help us to make any of the below.

1. Decision Making

2. Prediction

3. Pattern recognition

these things will help us to make better decisions on business plans, products to be launched, prioritising the priority work, and strategies that will make more revenues.

This is why companies invest a lot in data science.

In the upcoming post, we will learn about How an End to End data science project will be, and what are the opportunities in this domain.



Read More