Analytics with K Nearest Neighbor Classification

23:46 Amoeba Technologies 0 Comments


K Nearest Neighbor Classification

K Nearest Neighbor Classification is a pattern recognition algorithm. It is a non-parametric method used for classification and regression. In both cases, the input consists of the K closest examples.
we can consider each of the characteristics in our set as a different dimension in some space, and take the value an observation has for this characteristic to be its coordinate in that dimension, so getting a set of points in space. We can then consider the similarity of two points to be the distance between them in this space under some appropriate metric. The way in which the algorithm decides which of the points from the training set are similar enough to be considered when choosing the class to predict for a new observation is to pick the k closest data points to the new observation, and to take the most common class among these, thus called the k Nearest Neighbors algorithm.

The Algorithm
The algorithm can be summarized as:
1.    A positive integer k is specified, along with a new sample
2.    We select the k entries in our database which are closest to the new sample
3.    We find the most common classification of these entries
4.    This is the classification we give to the new sample.

The closeness can be identified by various distance measurements. Hence the distance method we choose effects the final results.
 


Example:

Let us Consider the following data concerning credit default. Age and Loan are two numerical variables (predictors) and Default is the target.


We can now use the training set to classify an unknown case (Age=48 and Loan=$142,000) using Euclidean distance. If K=1 then the nearest neighbor is the last case in the training set with Default=Y.
 
D = Sqrt[(48-33)^2 + (142000-150000)^2] = 8000.01  >> Default=Y
 

With K=3, there are two Default=Y and one Default=N out of three closest neighbors. The prediction for the unknown case is again Default=Y.

K-Nearest Neighbor algorithm in case of high number of dimensions and low number of training samples, "nearest" neighbor might be very far and in high dimensions "nearest" becomes meaningless. It is an easy to understand algorithm and handling of missing values is effective (restrict distance calculation to subspace).

Thanks and Regards,
Amoeba Technologies Core Team | info@amoebatechno.com
www.amoebatechno.com | 24 x 7 Support No: +91-8886516000
Facebook: https://www.facebook.com/AmoebaTechnologies

 

0 comments :

Have you heard about R Programming. Here we clarify....

03:51 Amoeba Technologies 2 Comments


R Programming

Just a letter and may be a way to future!!
R is a simple user friendly language used for interpret, interact and visualize data. It’s a software for statistical programming environment and a generic programming language concepts as they are implemented in a high level statistical language. It is especially designed for data analysis faster than users of legacy software, with flexibility in mix and match models for better results. Practical issues involved are to program, read data, access packages, and provide working examples.

Why go for it?
Data Analytics and Management has many challenges for any industry. The major challenges being volume and frequency of data, variation, identification of the most valuable pools of data. These problems can be simply cleared by using this language. We can find, download and use best community reviewed methods in statistics and predictive modeling from leading scientists in data science without any charge. Yes it is absolutely free!!

Steps involved in getting to know about R language is pretty simple and quick. All we need to do is write our code initially and then improvise the data using statistics. We can reinstate the data sets to figure out better analysis of the data. Data visualization can be done through various interactive plots and then, comes the final step of big data.
 

What’s so special about it?

R represents complex data showing beyond bar and line plots. Multidimensional data with multi-panel charts, 3-D surfaces and many more interesting info-graphs can be plotted. R programs are easily scripted and understandable for further passing on to produce research and deployable production.

Well, keeping things aside, R is used by data scientists worldwide to create social and media marketing to developing financial and climatic models that helps driving our economy and community.

We can sit back to observe the world changing with this software!!

Thanks and Regards,
Amoeba Technologies Core Team | info@amoebatechno.com
www.amoebatechno.com | 24 x 7 Support No: +91-8886516000
Facebook: https://www.facebook.com/AmoebaTechnologies

 

2 comments :

Know what Predictive Analysis is all about

03:47 Amoeba Technologies 0 Comments


Predictive Analysis

Can we know our future? Well, an interesting field to discuss. An enthusiastic reply would be may be or a yes. But clearly relying on such prediction for our daily needs? Can we think of the level of uncertainty and still proceed?

With an emphasis on the past data, upon rapid analyzing gives future predictive results which can be useful for business interests. Not just in for Business interests, we have been following these predictions in our daily activities without even thinking about it. And hence thereby we can influence the future simply from the data. Listening to data gives the best clues for our future.

“Will you get Diabetes as a heredity?”
“Will your company run in future with effective profits considering the inflation rates?”

“Stock prices to rise or fall”

Well the process is simply to get an insight into the data but cannot confirm anything for sure.



Where and how can we use it?
Predictive Analytics and data mining solutions for the enterprise are currently available from a number of companies including SAS (Predictive Analytics Suite), IBM (SPSS) and Microsoft (Dynamic CRM Analytics). Predictive analytics software can be deployed on premises for users or in cloud platform for team based initiatives.

How it works?
Predictive Analysis basically involves combining capabilities of predictive modeling, Big Data mining, Real-time Business Intelligence (BI), Data visualization and more to check emerging trends. These disciplines also involve rigorous data analysis, and are widely used in business for segmentation and decision making, but different purposes and the statistical techniques underlying them vary. We can detect and prevent threats to guide frontline decisions with future insights.

Can group of predictions make the future?
There have been many more interesting improvements in the core technology of predictive analytics. Persuasion modeling, which predicts influence - in order to do influence. The Obama campaign used it for 2012 presidential election; marketing uses it to persuade customers; and medicine uses it for selecting better patient treatments. Like the collective intelligence that spawns the wisdom of a crowd of people, we see the same effect with a crowd of predictive models. Each model alone may be totally primitive as of a few simple rules, so it might get prediction wrong a lot, as an individual person trying to predict also does. But having them come together as a group and there emerges a new level of predictive performance.

 
Thanks and Regards,
Amoeba Technologies Core Team | info@amoebatechno.com
www.amoebatechno.com | 24 x 7 Support No: +91-8886516000
Facebook: https://www.facebook.com/AmoebaTechnologies

 

0 comments :

Do you know what is Data Analytics and its purpose

03:44 Amoeba Technologies 0 Comments



Data Analytics

What is Data Analytics?
Data Analytics is an opportunity to find insights in types of data and content, to make the business more agile, and to answer questions that were previously considered beyond reach.

Why, we need to do it?
Every day, we create 2.5 Quintillion (10^18) bytes of data of which 90% of the data in the world today has been created in the last two years alone!!

Benefits of this includes creation of new products and services for customers. For example GE has made a huge investment in new services for its industrial products using data analytics. Apart from cost reduction using the data, faster and better decisions can be taken.



 
Challenges:
Getting data from various sources and in various formats, data analysis can be a challenge. The ability to import the data from these sources and analyze them to see the big picture is variably important. The data can be used to formulate Key Performance Indices (KPI’s).

We can identify relationships, patterns and analogies involving comprehensive analysis of data by using various techniques like regression, clustering to name a few.

Does this simply means proliferations of data is an evidence for an intrusive world? Or the data will play a useful economic model? With an understanding of how big the data is, harnessing it involves workforce to support business decision making and economic growth. To enable effective decision making it is important to have the potential value that big data can create economic benefits for organizations and sectors.

This article is just to bring awareness about the jargon of Data Analytics and we will take it up to the next of details and understanding in the coming set of articles. Happy Reading friends!!!

Thanks and Regards,
Amoeba Technologies Core Team | info@amoebatechno.com
www.amoebatechno.com | 24 x 7 Support No: +91-8886516000
Facebook: https://www.facebook.com/AmoebaTechnologies

0 comments :