3.1Data Driven Models Flashcards
What is Analytics
Analytics denotes the set of methods, techniques, heuristics, and processes of analysing data in order to find valuable information
How is the data flow in the DT
Which kind of analytics do we have?
Traditional Analytics
Type of analytics does not need complex methods but common practices.
Advanced Analytics
Use of more complex methods, available in statistics,
mathematics, artificial intellience, etc.
How are the analytics methods divided
The analytics are divided in** INTENDED METHODS NOT IN CATEGORIES**. We must be able to visualize the data in order to see the changes on it, how is it evouluating
What is the difference between “Artificial Intelligence and Data mining”
Artificial intelligence: The machine try to mimic human intelligence eg language and communication.
Data Mining. it discovers patterns in data. It realize in human interpretation
What is Machine learning
We try to learn machines from the experience, and this in two ways. Supervised And Supervised
“The set of computational methods that automate
the acquisition of knowledge from experience.”
What is the machine learining structure?
Two types of models, supervised and unsupervised. Supervised, use labels and targets, these are knwon, are sorted…Unsupervised learning. is based in similarities
What does traning and test and datasets means. What are the attention points.
From your data set, you choose a training set that has to be trained, you train your data and you test it, then you set a reference for the qualification a kind of meassurement, afterwards you take your “measurement/reference” and apply it or test it on the Test Set it. If your Test is correct it will fit the measurement or reference from the training set. Be aware, all the labels must be known in the Training Set and Test set
What is supervised learning
Supervised learning is a machine learning approach that’s defined by its use of labeled datasets. These datasets are designed to t**rain or “supervise” algorithms **into classifying data or predicting outcomes accurately. Using labeled inputs and outputs, the model can measure its accuracy and learn over time.
What is unsupervised learning
Unsupervised learning uses machine learning algorithms to analyze and cluster unlabeled data sets. These algorithms discover hidden patterns in data without the need for human intervention (hence, they are “unsupervised”).
Unsupervised learning models are used for three main tasks:** clustering, association and dimensionality reduction:**
Describe semi supervised learning?
This method works like in trial and error, you teach your algorithm to do something, when he does something good, you give him a reward and safe this action, and when not you discard this action, so you only keep the good moves
Describe the machine learning modeling flow.
What are the three steps and what happend on then
Algorithms
