Scribd
Upload
2 views11 pages

08 - Build The Models

The document outlines a structured process for building data science models, starting from understanding the business problem to deploying the model in production. Key steps include data collection, preparation, analysis, training, evaluation, and execution using programming languages like Python. The ultimate goal is to enhance predictions and insights while ensuring team collaboration and cost-effectiveness.

Uploaded by

theophilusindia
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
2 views11 pages

08 - Build The Models

The document outlines a structured process for building data science models, starting from understanding the business problem to deploying the model in production. Key steps include data collection, preparation, analysis, training, evaluation, and execution using programming languages like Python. The ultimate goal is to enhance predictions and insights while ensuring team collaboration and cost-effectiveness.

Uploaded by

theophilusindia
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11

Build the models

Step 1: Understanding Business


Problem
o Data scientists must understand the business
problem they are trying to solve.
o Understanding the data science process and
the ultimate objective helps measure ROI.
Step 2: Data Collection

o Data collection gathers relevant data, both structured and


unstructured.
o Well-known data repositories include Dataset Search Engines,
Kaggle, NCBI, and UCI ML Repository.
Step 3: Prepare Data

o Data needs to be shaped to train the data science


model.
Step 4: Analyze patterns in Data

o Identify patterns and trends in cleaned data.


o Use tools like Microstrategy and Tableau to build
intuitive dashboards.
Step 5: Training Model Features

o Train the model with data by applying different algorithms


and techniques.
Step 6 : Model Evaluation

o Assesses various metrics to decide if the model is


successful.
o Manages the decision of learning strategy or model.
Step7 : Putting Model into Production

o This phase tests the model's real-world performance.

o Also known as "operationalizing" the model.

o Involves deploying the model and constantly measuring its performance.


Presenting and Building Applications

o A structured approach maximizes success and cost-


effectiveness.
o Enables team collaboration with each member focusing on
their strengths.
Building the Models

o With clean data and a good understanding of the content, models are
ready to be built.

o Goal is to make better predictions, classify objects, or gain an


understanding of the system.
Model Execution

o Programming languages like Python have libraries (StatsModels, Scikit-


learn) for popular techniques.

o Coding models can be complex, so these libraries speed up the process.

o Example: Executing a linear regression model using Python.

You might also like