What is Data Science?
Data Science is the function of extracting actionable insights from data, using algorithms, data tools and human processing power. This function often includes
Is a Data Scientist the same as a Data Analyst?
While much has been written about A.I and the technology that powers Data Science, machine learning is still incapable of differentiating between truly useful (actionable) results and informational results. The is the role of a Data Analyst. In organisations where data volumes justify role separation, a Data Scientist will manage data and create reports, while a Data Analyst will interpret the reports to develop tactical plans and competitive strategies.
Who uses Data Science?
There is a common misconception that Data Analytics is only used by and useful for Medium to Enterprise level organisations, and only in certain sectors. This is untrue. The Internet of Things has created a world of multiple points of data collection that a business in any industry can utilise for decision making. Even small businesses can learn the simplest data analytics techniques to generate useful reports.
What are some common Data Science tools?
The necessity of particular Data Analytic tool is dependent on the volume of data that needs to be managed, and the number of sources generating the data. For SMEs, understanding website traffic, simplified trend analysis or product-channel revenue optimisation is a good starting point and can be generated with small data sets. Google Analytics is an excellent tool for analysing website traffic and there are free courses available on Google Analytics Academy on how to use it effectively. Additionally, Microsoft Excel is a great data management and analytic tool, and its ubiquitousness makes it the easiest Data Science tool to master. More suitable software for large volumes of data is software such as Apache Spark and Tableau.
What Technical Skills do you need to specialise in Data Science?
What is CRISP-DM in Data Science?
CRISP-DM stands for cross-industry process for data mining. It is an open-standard methodology that provides a structured approach to mining and shaping data. It is a capstone of Data Science and follows a six-step process;
- Business understanding – Determine the desired project output
- Data understanding – Collect, describe and explore the data
- Data preparation – Identify data to be used and justify rationale
- Modelling – Determine modelling technique, test design and build the model
- Evaluation – Analyse, review and evaluate results
- Deployment – Plan execution, deploy, monitor and produce report