The phases of the data life cycle are very important on this business context. Weather organization need to run business for long term or short time want to make sure will follow the cycle of data. The phases of the data cycles are attended to throughout the entire Data Analytics life cycle plan. We follow step by step procedure to complete the entire life cycle. These phases are a great guideline for our plan and following them will make our plan handy and complete the task on timely manner while focusing on our raw for the whole life cycle. The phases of the data analytics life cycle are data discovery, data preparation, model planning, building, results, and operationalize.
Discovery: Discovery is the first phase of Data Analytics life cycle. It is a business user-oriented process for detecting patterns and outliers by visually navigating data or applying guided advanced analytics. This is when we must implement tools and software. First team will discover the business problem. Then they will study the list of dataset or pattern and ask question “what’s wrong with this dataset”? This process is coming to build entire planData Preparation: One of the biggest challenging in business world is data preparation. This phase will play an important role in our data plan because we want to make sure appropriate data is enter into the system. When building a data preparation, Team really want it to be correct the first time you do it.
Changes are possible, but they are painful. This process involved CRUD (Create, Read, Update, Delete), developing database, document the structure of the dataset and many more. Once this data is done, then will move to next phase which is planning.Model planning: Model planning is one of the important effect of modeling a plan. This is when we model planning the data before we move to next phase for building model.
This plan will assist us and determine any problem that might come in near future for long term business goal. In phase 3 team will determine the methods, technique, brainstromig and many more. Now we can use a diagramming piece of software like Visio, drawio.io or SharePoint to model planning., all team really need to model a database. pencil and paper and be prepared to think deeply about a data to learn about the relationships between two variables and subsequently selects key variables and the most suitable models(Shah)Model building: In phase 4 team develop a dataset, select a mathematical model and algorithms to solve the business problem.
This process is done based on the work done in the planning phase. The team also plan weather existing tool are required to perform model and overflows. For example, if QlikView is not best solution to perform the job, team might have to go with tableau. Team will have decided whether existing tool is great, or they required new tool.Communicate results: It is the one of the important phase in data analytics life cycle. The team will collaborate with stakeholders whether the project will be success or failed based on the planning developed in phase 1 discovery. In this phase, we will determine if have enough information to succeed in the plan or we need alternative solution.
For example, weather team need to communicate with other data analytics, stakeholders or users. On this phase result can be communicate through oral or verbal.to solve business problem. Weather team need to have meeting, discussion board or other communication tool, team need to communicate and summarize the step to stakeholders.Operationalize: This is the last and final phase of data life cycle. In final phase we deliver the Final report briefing the business scenario, code, implementing methods and technical document within the organization (Shah 2018). Once final phase is done, we will complete our reports and make sure all answer was question.
This phase also involved team need to implement the model in production environment.Each phase will give us an appropriate result. Each phase will help us given a best result. The outputs are based on the business context which we are working because we don’t need all the data to build this company from scratch. Some of the data is already exist in the system. We are still following the 6-data analytics life cycle.
Below are the few of the output the higher and more output we receive, there is a chance we will be able to get rid of useless data. Any data analyst project will support our conclusion because we follow the best research and judgmental decision. Some of the expected output we might get from each phase are as followsØ Team get an opportunity to discover the data and figure it out what need to be doneØ We want to ensure all data are correct in computer. Only accurate data will be entre on the systemØ Will plan data through Visio, brain storming, and creativity think outside the box.
Team who does not know how to use planning tool, they get an opportunity to know this toolØ Will use different technique and tool to build the data model. Team also get an opportunity to try different technology toolØ Communicate with stakeholders to ensure they are happy with our business contextØ We want to ensure once all step process. Will show full report to our stakeholders, audience and user.
The audience, stakeholders, and users will play an important role on this data plan. They are the backbone of the company. They don’t need to be involved until the end.
Depend on the issue we are facing and accomplish this business for long term. I do not believe they really need to be use until final phase. Team will still be communicating with the audience, stakeholders and user. However, team will focus more on Data Analytics life cycle first and then they involved all other sponsors and stakeholders on this data plan. They will however not really be needed in our scenario until the end. The audience is the country, travel agency and the workers, the stake holders are the people who sponsor money to run off the ground and the users are those who are using our service such as passenger.