DAT205_Assignment2

Assignment 2

IBM Cognos Analytics Software Tool for Analyzing Trends in House Prices Dataset

What was the IBM Cognos Analytics Software Tool and why was it good for usage to

“self-service with intuitive web-based interface to upload and analyze the data,” “supports visual

data exploration without writing any code,” “drag and drop data onto the canvas and made

updates to suite analysis,” “the system recommends visualization based on selected fields and

based on currently open visualization,” “you may build interactive dashboards and stories,” and

“show data for an individual visualization” (Knode, 2019) The tool allowed the Data Scientist to

focus on finding the trend for the house prices by analyzing the data. Also the Data Scientist

examined the correlation among the variables of the house prices dataset.

The cleansing of the house prices dataset by the Data Scientist has to be performed to

“eliminate mistakes, bad records, data entry errors, and outliers” (Knode, 2019) before the Excel

spreadsheet can be uploaded into the Cognos Analytics software tool. For example the country

be cleansed or filtered out because when the realtor works with the seller and/or buyer, the house

prices could not have decimal points. The house prices were normally round to the nearest one

dollar. i Next, the Data Scientist acknowledged that the house prices with the $0 rows were

accidentally entered by the data entry person. i These rows needed to be deleted. i

The following house prices data variable price will be examined using Cognos Analytics

sqft_lot, floors, waterfront, view, condition, sqft_above, sqft_basement, yr_built, yr_renovated,

street, city, and statezip. Based upon the Data Scientist’s knowledge and experience with the real

estate market in the United States, he has insights into how the house prices dataset will turned-

out when the dataset is placed into the Cognos Analytics Software Tool for further analysis. The

Data Scientist noticed that the price to statezip data’s relationship strength is 41% which is the

highest when comparing the price variable to other variables. i Next in relationship strength was

the price to city at 37%, followed by the following variables: price to sqft_living at 35%, price to

sqft_above at 28%, price to bathrooms at 28%, there was a tie for price to bedrooms at 18% and

also price to floors at 18%, lastly price to view at 16%, and lastly price to sqft_basement at 15%.

The Data Scientist saw that price has no relationship strength with the following variables:

waterfront, condition, yr_built, yr_renovated, and street which is pretty accurate because where

the Data Scientist lives, these variables are not taken into account when he used the

www.realtor.com website to analyze how much is the current price of the house. i Also the Data

Using the Cognos Analytics Software Tool, the Data Scientist further examined the price

to statezip data’s relationship strength at 41% and to find out the average values of the price

WA 98047) to a maximum of 2,046,559.091(when Statezip is WA 98039).” See photo of IBM

Then the Data Scientist used the Cognos Analytics Software Tool to examine the

Predictive strength of the house prices dataset using the Spiral Diagram for first data

visualization. i “The combination of Sqft Living, Statezip, City, View, Floors, and Date is a

predictor of Price” with the Predictive strength of 66%. i The Predictive strength helps the Data

Scientist to “understand the importance of a field in relationship to its ability to its ability to help

predict the outcome.” i In other words, the bigger the percentage of the Predictive strength, “the

stronger correlation it has with what is be predicted.” The photo from the IBM Cognos Analytics

Software Tool depicts this.

A second data visualization used and it was called Decision Tree. “A decision tree shows

a connected hierarchy of boxes to represent the values of records.” Furthermore the Data Scientist

reviewed Tree sunburst tab and he finds out “that if the measures within the decision tree are

A third data visualization called Scatterplot Graph which shows the relationship between

area increases the price increases.

A fourth data visualization called Boxplot Graph with error lines to understand price by zip code.

From the below boxplot graph Data Scientist can see the range of zip 98004 is quite big and that

zip has the highest sum of prices of the houses.

A fifth data visualization called Bar Graph shows the relationship between price of the houses and

the year built. Data Scientist can see that the trend shows that as the year built increases the price

of houses increases which is true in general as the property is new it’s valued more compared to

an older property.

dataset, Data Scientist needed a good analytics software tool like the IBM Cognos Analytics

Software Tool to find out the trends and do the data analysis. But before the Data Scientist can

upload the dataset into the Cognos Analytics, the dataset must be examined to “eliminate

mistakes, bad records, data entry errors, and outliers” (Knode, 2019). i Then the Data Scientist

reviewed the correlation among the variables of the dataset. There were five noticeable data

visualizations and they were the Spiral Diagram which shows the relationship strength of the

price with the other variables, Decision Tree to show the predictive strength, Scatterplot Graph,

Boxplot Graph, and the Bar Graph. i

References

IBM. Retrieved from

https://www.ibm.com/support/knowledgecenter/SSEP7J_11.1.0/com.ibm.swg.ba.cognos.ca_expl

orations.doc/ca_explorations.pdf?view=kc

IBM. Retrieved from

https://www.ibm.com/support/knowledgecenter/SSEP7J_11.1.0/com.ibm.swg.ba.cognos.ug_ca_

dshb.doc/wa_discover_explore_intro.html

IBM. Retrieved from

IBM. Retrieved from https://dataplatform.cloud.ibm.com/analytics/notebooks/3e83ffa1-f52a-4b76-

bbb5-

498b6b7f9505/view?access_token=a7dfdd01dbc24c53a5ac9688fbdd32da1b59156117d721fe10d12660f

18dd591

IBM. Retrieved from

https://www.ibm.com/support/knowledgecenter/en/SSEP7J_11.0.0/com.ibm.swg.ba.cognos.ug_ca_dsh

b.doc/wa_an_hlp_adjust_intro.html

IBM. Retrieved from

https://www.ibm.com/support/knowledgecenter/en/SSEP7J_11.1.0/com.ibm.swg.ba.cognos.cbi.doc/w

elcome.html

https://www.ibm.com/support/knowledgecenter/SSEP7J_11.1.0/com.ibm.swg.ba.cognos.ca_gtstd.doc/

ca_gtstd.pdf

IBM. Retrieved from

https://www.ibm.com/support/knowledgecenter/SSEP7J_11.1.0/com.ibm.swg.ba.cognos.ca_exploratio

ns.doc/ca_explorations.pdf?view=kc

Knode, Steve (2019, Summer). University of Maryland University College. Retrieved from

Knode, Steve (2019, Summer). University of Maryland University College. Retrieved from “Intro

to Cognos analytics.pptx”

Knode, Steve (2019, Summer). University of Maryland University College. DATA 610 –

Decision Management Systems. Retrieved from Assignment No. 2 – Exploratory Data Analysis

(EDA) using Cognos Analytics.

Knode, Steve (2019, Summer). University of Maryland University College. Retrieved from

Knode, Steve (2019, Summer). University of Maryland University College. Retrieved from

Knode, Steve (2019, Summer). University of Maryland University College. Retrieved from

https://www.youtube.com/watch?v=8tYV42SUGGY