Subscribe to DSC Newsletter
Maiia Bakhova
  • Female
  • San Diego
  • United States
Share

Maiia Bakhova's Friends

  • Scott Sobel

Gifts Received

Gift

Maiia Bakhova has not received any gifts yet

Give a Gift

 

Maiia Bakhova's Page

Latest Activity

Maiia Bakhova liked Vincent Granville's blog post Massive Internet Attack Floods the World with Fake Data
Dec 6, 2016
Maiia Bakhova commented on Vincent Granville's blog post Massive Internet Attack Floods the World with Fake Data
"As Russian native I've have seen this kind of fake news influx in Russian social networks for last couple of years. In particular, a huge number of lies has been orchestrated about Russian aggression to Ukraine, to the point that people do not…"
Dec 5, 2016
Pradeep Naulia commented on Maiia Bakhova's blog post Choosing features for random forests algorithm
"Just clarifying my assumption, is it u r assuming that each mode is near pure majority class of a separate class or group, alternatively each mode is able to discriminate between classes effectively. Pls let me.know"
Nov 15, 2016
Maiia Bakhova posted a blog post

Detection of Practical Dependency of Variables with Confidence Intervals

This is an article which attempts to detect dependable variables with non-linear method.I'm going to apply a method for checking variable dependency which was introduced in my previous post. Because the "dependency" I get with this rule is not true dependency as defined in Probability then I will call variables practically dependent at a confidence level "alpha", where "alpha" is a…See More
Nov 2, 2016
Clancy Birrell liked Maiia Bakhova's blog post Measuring Dependence of Variables with Confidence Intervals.
Sep 8, 2016
Maiia Bakhova liked Emmanuelle Rieuf's blog post Precision vs significance / accuracy vs precision / bias vs variance
Sep 8, 2016
Darrel Dent liked Maiia Bakhova's blog post Measuring Dependence of Variables with Confidence Intervals.
Sep 7, 2016
Maiia Bakhova liked Vincent Granville's blog post Black-box Confidence Intervals: Excel and Perl Implementation
Sep 7, 2016
Maiia Bakhova's blog post was featured

Measuring Dependence of Variables with Confidence Intervals.

In this post I will sometimes use a term “variable” for “feature”(“predictor”“) or”outcome“(”predicted value“”).The question of variable dependencies for a particular data is quite important, because it can help to reduce an amount of predictors used for a model. Or it can tell us what feature is not helpful for a model construction, although it still can be used for engineering of another predictor. For example sometimes it is better to compute speed than to use distance values. In addition…See More
Sep 6, 2016
Maiia Bakhova posted a blog post

Measuring Dependence of Variables with Confidence Intervals.

In this post I will sometimes use a term “variable” for “feature”(“predictor”“) or”outcome“(”predicted value“”).The question of variable dependencies for a particular data is quite important, because it can help to reduce an amount of predictors used for a model. Or it can tell us what feature is not helpful for a model construction, although it still can be used for engineering of another predictor. For example sometimes it is better to compute speed than to use distance values. In addition…See More
Sep 6, 2016
Georges Bressange liked Maiia Bakhova's blog post Improving performance of random forests for a particular value of outcome by adding chosen features
Jun 14, 2016
Maiia Bakhova updated their profile
May 18, 2016
Maiia Bakhova posted a blog post

Visualizing Bagged Trees as Approximating Borders

The bagged trees algorithm is a commonly used classification method. By resampling our data and creating trees for the resampled data, we can get an aggregated vote of classification prediction. In this blog post I will demonstrate how bagged trees work visualizing each step.…See More
May 18, 2016
Alastair Muir liked Maiia Bakhova's blog post Improving performance of random forests for a particular value of outcome by adding chosen features
May 10, 2016
Maiia Bakhova's blog post was featured

Improving performance of random forests for a particular value of outcome by adding chosen features

Choosing features to improve a performance of a particular algorithm is a difficult question. Currently here is PCA, which is difficult to understand (although it can be used out-of-the-box), requires centralizing and scaling of features and is not easy to interpret. In addition, it does not allows to improve prediction performance for a particular outcome (if its accuracy is lower than for others or it has a particular importance). My method  enables to use features without preprocessing.…See More
May 7, 2016
Maiia Bakhova posted a blog post

Improving performance of random forests for a particular value of outcome by adding chosen features

Choosing features to improve a performance of a particular algorithm is a difficult question. Currently here is PCA, which is difficult to understand (although it can be used out-of-the-box), requires centralizing and scaling of features and is not easy to interpret. In addition, it does not allows to improve prediction performance for a particular outcome (if its accuracy is lower than for others or it has a particular importance). My method  enables to use features without preprocessing.…See More
May 7, 2016

Profile Information

Short Bio
Mathematics PhD seeking a Data Scientist position at a progressive tech company. I have diverse data-manipulation experience critical to answering thoughtful scientific and marketplace questions. I apply a thorough and creative perspective to problem solving, and readily develop new skills to address yet unanswered problems. I am proficient in multiple computer languages, have experience presenting and teaching to diverse audiences, and am passionate about big data technologies.
Here is my data science blog:
http://myabakhova.blogspot.com
My Web Site Or LinkedIn Profile
http://www.linkedin.com/in/myabakhova
Field of Expertise
Analytics, Visualization, Big Data, Data Science
Professional Status
Other
Your Job Title:
Data Scientist
How did you find out about DataScienceCentral?
linkedin.com
Interests:
Finding a new position, Networking

Maiia Bakhova's Blog

Detection of Practical Dependency of Variables with Confidence Intervals

Posted on November 2, 2016 at 11:30am 0 Comments

This is an article which attempts to detect dependable variables with non-linear method.

I'm going to apply a method for checking variable dependency which was introduced in my previous post. Because the "dependency" I get with this rule is not true dependency as defined in Probability then I will call variables practically dependent at a confidence level…

Continue

Measuring Dependence of Variables with Confidence Intervals.

Posted on September 6, 2016 at 1:07pm 0 Comments

In this post I will sometimes use a term “variable” for “feature”(“predictor”“) or”outcome“(”predicted value“”).

The question of variable dependencies for a particular data is quite important, because it can help to reduce an amount of predictors used for a model. Or it can tell us what feature is not helpful for a model construction, although it still can be used for engineering of another predictor. For example sometimes it is better to compute speed than to use distance values. In…

Continue

Visualizing Bagged Trees as Approximating Borders

Posted on May 18, 2016 at 2:12pm 0 Comments

The bagged trees algorithm is a commonly used classification method. By resampling our data and creating trees for the resampled data, we can get an aggregated vote of classification prediction. In this blog post I will demonstrate how bagged trees work visualizing each step.…

Continue

Improving performance of random forests for a particular value of outcome by adding chosen features

Posted on May 5, 2016 at 11:30am 0 Comments

Choosing features to improve a performance of a particular algorithm is a difficult question. Currently here is PCA, which is difficult to understand (although it can be used out-of-the-box), requires centralizing and scaling of features and is not easy to interpret. In addition, it does not allows to improve prediction performance for a particular outcome (if its accuracy is lower than for others or it has a particular importance). My method  enables to use features without preprocessing.…

Continue

Comment Wall (1 comment)

You need to be a member of Data Science Central to add comments!

Join Data Science Central

At 6:06am on February 22, 2016, Scott Sobel said…

Sure, I will do that. Thank you for your insights...

 
 
 

Follow Us

Videos

  • Add Videos
  • View All

Resources

© 2017   Data Science Central   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service