Welcome to Comparing ETL and ELT. After watching this video, you will be able
to: List key differences between ETL and ELT. Describe ELT as an evolution of ETL. Describe the trending shift from ETL to ELT. Differences between ETL and ELT: For one thing, the transformations happen
in a different order: Transformations for ETL pipelines take place
within the data pipeline, before the data reaches its destination, whereas Transformations for ELT are decoupled from
the data pipeline, and happen in the destination environment at will. They also differ in flexibility in how they
can be used: ETL is normally a fixed process meant to
serve a very specific function, whereas ELT is flexible, making data readily available
for self-serve analytics. They also differ in their ability to handle
Big Data. ETL processes traditionally handle structured,
relational data, and on-premise computing resources handle the workflow. Thus, scalability can be a problem. ELT on the other hand, handles any kind of
data, structured and unstructured. To handle scalability problems posed by Big
Data, ELT leverages the on-demand scalability offered by cloud computing services. With regard to data discovery and time-to-insight: ETL pipelines take time and effort to modify,
which means users must wait for the development team to implement their requested changes. ELT provides more agility. With some training
in modern analytics applications, end users can easily connect to and experiment with
the raw data, create their own dashboards, and run predictive models themselves. ELT is a natural evolution of ETL. One of the factors driving that evolution
is the demand to release raw data to a wider user base for the enterprise. Traditionally, ETL processes include an intermediate
storage facility called a staging area. This is a holding area for raw extracted data,
where you can run processes prior to loading the resulting transformed data into a data
warehouse or a data mart. This sounds a lot like an ELT process, and
the staging area fits the description of a data lake, which is a modern self-serve repository
for storing and manipulating raw data. A traditional staging area, however, is not
something that is usually shared across the company. It's a private, siloed area set aside
for developing, monitoring, and performance tuning the data pipeline and its built-in
transformations. Along with the ever-increasing ease-of-use
and connection capabilities of analytics tools, raw data sources have become much more accessible
to less technical end users. Accordingly, the paradigm is shifting to self-service data
platforms. There is still a place for conventional
ETL in developing data products, so ETL is not disappearing any time soon. However, there is a trend taking place – a
trend which is favoring modern ELT over conventional ETL. The trend is being driven by the pain points
that ELT solves, namely, the lengthy time-to-insight the challenges, for example, scalability,
imposed by Big Data, and the conventional siloed nature of data. In this video, you learned that: Key differences between ETL and ELT are
the location where the transformation takes place, flexibility, Big Data support, and
time-to-insight. One of the factors driving the evolution
from ETL to ELT is the demand to release raw data to a wider user base for the enterprise. Conventional ETL still has many applications,
and still has its place. ELT is more flexible than ETL, enabling end-users
to perform ad-hoc, self-serve data analytics in real-time.