To track problem points in the business

To understand the business goals

To analyze historical data

To identify future trends

Identifying the problem

Cleaning the data

Aggregating the data

Determining which data you need

Data collected from social media

Data collected from open sources

Data collected from various sources

Data collected directly from customers

First party data

Second party data

Third party data

Unstructured data

Adding more errors

Introducing outliers

Removing duplicates

Including irrelevant observations

After defining the question

After analyzing the data

Before collecting the data

Before defining the question

Identifying future trends

Understanding why something has happened

Identifying what has already happened

Analyzing historical data

Identifying future trends

Understanding why something has happened

Identifying what has already happened

Analyzing historical data

Classification

Regression

Clustering

Linear Programming

1. Association and correctional analysis classification

1. Cluster analysis and Evolution analysis

1. Prediction and characterization

1. All of the above

Retail

Finance/Banking

Manufacturing

All of these

y=mx+b

a^2+b^2=c^2

(1/2)(b)(h)

The more books students read, the lower their English grade.

The more books students read, the higher their English grade.

The fewer books students read, the higher their English grade.

No relationship exists between the number of books students read and their English grades.

There is a strong positive correlation between studying and grades.

There is a strong negative correlation between studying and grades.

There is a weak positive correlation between studying and grades.

There is a weak negative correlation between studying and grades.

People type at a speed of -1.4 words per minute

For every year passed, your typing speed decreases by 1.4 word per minute

The fastest person types at 117.8 words per minute

For every word typed, -1.4 minutes go by

True

False

Yes

No

True

False

$$f(z)=1/(1+e^{-z})$$

$$f(z)=1/(1+e^z)$$

$$f(z)=1/(1+e^{-z})+1/(1+e^{-z})$$

$$1/(1+e^{-z})-\ 1/(1+e^{-z})$$

It has a bell-shape graph and its values ranges from -1 to 1

It has a narrow bell-shape graph and its values ranges from -2 to 2

It has an s-shape and its values ranges from 0 to 1

It has parabolic-shape graph and its values ranges from 0 to 2

To maximize the dissimilarity of observations within a cluster and maximize the similarity between clusters

To maximize the similarity of observations within a cluster and maximize the dissimilarity between clusters

To minimize the dissimilarity of observations within a cluster and maximize the similarity between clusters

To minimize the similarity of observations within a cluster and maximize the dissimilarity between clusters

market and image segmentation

market segmentation only

image segmentation only

none of the above

Classification predicts a numerical output , given input data while Clustering groups data points based on similarities among them and differences from others

Classification predicts an output category, given input data while Clustering groups data points based on dissimilarities among them and similarities from others

Classification predicts an output category, given input data while Clustering groups data points based on similarities among them and differences from others

R-squared should be used to compare the models.

R squared can be interpreted as the percentage of variation of y that is explained by the model.

R squared can decrease if correlation between y and additional x is zero.

The lower the R-squared, the better the model is.

Do not have a natural order

Blood type one of nominal data

Relate to ranking

Socio economic is call as nominal data

two different value is meaningful

Temperature one of ordinal data

Has all the properties of an variable

Pulse is ordinal data

qualitative

quantitative

qualitative

quantitative

range

median

quartile

mode

mean

mean

median

mode

range

mean

median

mode

range

mean

median

mode

range

The sales of chocolate dropped drastically followed by another notable drop to 10%. It then skyrocketed in April at 50% before dropping moderately to 40%

Chocolate sales took a nosedive in February from 70% to 20% and it decreased yet again quite reasonably before plunging significantly in April. However, the sales dwindled again to 40% in the last month

The sales of chocolate descended substantially to 20% in February. This is followed by another moderate reduction of 10% before the sales boomed to 50% and went down slightly again in the last month.

The percentage of chocolate sales plunged considerably in the first 2 months and suffered another substantial fall in the next month. It then recovered with a steady climb before it dipped slightly to 40% in May

In the 14-18 age group, the preference for biscuits, chocolate and ice cream all ranged below 55%. The difference between potato chip and biscuits preference was quite small at 20% compared to with ice cream at a large percentage of 40%.

In the 9-13 age group, those who prefer chocolate showed the highest percentage at 50% which the lowest was potato chips at only 30%. The percentage of those who preferred chocolate in this age group was the same as in the 4-8 age group at 50%

In the 4-8 age group,those liking potato chips recorded the lowest percentage at 20% while those who preferred ice cream triumphed with the highest percentage of 70%. The range of preference for biscuits and potato chips was lower than 35%

y= 2x+3

y=3x+2

y= $$\frac{1}{2}x\ +3$$

y= $$-\frac{1}{2}x\ +3$$

y= -2x + 10

y= 10x+ 2

y=2x+10

y= 10

$$y=-0.83x+0.61$$

$$y=-0.83x+0.63$$

$$y=0.83x+-0.8$$

$$a^2+b^2=c^2$$

y = 1.5x + 12

y = 12x + 1.5

y = 0.67x - 8

y = -8x + 0.67