Assignment 1
Quynh Nguyen Thi Nhu
2025-03-21
## NULL##
## 1 function (x, df1, df2, ncp, log = FALSE)
## 2 {
## 3 if (missing(ncp))I. Visualization
1. Histograms
Fig. 1.1
Output:
- The Administrative department has employees with satisfaction scores mostly clustered at the higher end of the scale.
- The Maintenance department shows employees with only a narrow range of satisfaction scores, indicating consistency in their responses.
- The Management department has employees with satisfaction scores in a tight range, mostly in the high satisfaction category, suggesting overall contentment in leadership roles.
- The Production department has a more varied distribution, with most employees reporting satisfaction scores between 6 and 9, suggesting a more diverse range of experiences.
- The Quality Control department has a few employees reporting only high satisfaction scores, indicating an overall positive experience.
- The Shipping/Receiving department shows a mixed distribution of satisfaction scores, with a few employees in the lower range but others in the mid to high range, suggesting varying perceptions of job satisfaction within the department. _________________________________________________________________________________________
2. Box plots for categorical variables
Fig. 1.2
Output:
- Employees with low recognition (1-2) have lower satisfaction scores with a wider spread, while those with high recognition (5) report consistently high satisfaction, showing a strong positive relationship.
- Employees with higher training levels (5) tend to have higher satisfaction scores, while those with lower training (2-3) show greater variability and lower satisfaction.
- Better working conditions correlate with higher satisfaction, as employees rating conditions 4-5 show higher median satisfaction scores compared to those rating 2-3.
- Employees with better work-life balance (5) consistently report high satisfaction, whereas those with poor balance (2-3) have more variation and lower median satisfaction scores. _________________________________________________________________________________________
3. Scatter Plot
Fig. 1.3
Output:
The scatter plot illustrates the relationship between Years
in Job and Satisfaction Score.
- The negative trend (red regression line) suggests
that as years in the job increase, satisfaction tends to
decrease.
- Employees with fewer years of experience exhibit a
wider range of satisfaction scores, including both high
and low values. - Employees with more than 20 years
tend to have lower satisfaction scores, possibly
indicating job dissatisfaction over time.
- While variability exists, the overall trend shows a decline in
satisfaction as tenure increases.
_________________________________________________________________________________________
4. Heat Map showing pairwise correlations
Fig. 1.4
Output:
The heatmap visualizes pairwise correlations between
numerical variables in the dataset, with values scaled between 0
and 1.
- Satisfaction has a strong positive
correlation with Recognition (0.85) and
Ideas (0.72), indicating that employees who generate
more ideas and feel recognized tend to report higher satisfaction.
- Communication (0.63) also has a moderate
correlation with Satisfaction, suggesting that better workplace
communication is linked to improved employee satisfaction.
- Tools (0.2) shows a weak correlation
with Satisfaction, implying that access to tools alone does not
significantly impact job satisfaction.
- Years in Job (0) has no correlation
with Satisfaction, reinforcing the finding from Figure 1.3 that tenure
does not influence job satisfaction.
- The strongest relationship is between Ideas
and Recognition (0.85), indicating that employees who
contribute ideas are also more likely to feel recognized.
The color gradient highlights stronger correlations in red and
weaker correlations in yellow, making it easier to interpret
relationships between variables.
5. Stacked Bar Chart
Fig. 1.5
Output:
The stacked bar chart displays the proportion of employees with
high and low satisfaction across
different departments.
- The Production department has the highest
proportion of employees, with a mix of high
and low satisfaction, but the majority fall into the
high satisfaction category.
- Administrative, Maintenance, and Management
departments have smaller employee counts, with
a higher proportion of high satisfaction employees
compared to low.
- QC and SR departments also have a majority of
high satisfaction employees, with only a few reporting
low satisfaction.
- The negative values for low satisfaction provide a
clear diverging bar effect, making it easier to compare the proportion
of satisfied and dissatisfied employees.
_________________________________________________________________________________________
II. KNN
1. Implementation in R
| Department | Years | Ideas | Communication | Recognition | Training | Conditions | Tools | Balance | Satisfaction |
|---|---|---|---|---|---|---|---|---|---|
| Administrative | 16 | 2 | 3 | 2 | 2 | 4 | 5 | 2 | 0 |
| Administrative | 2 | 4 | 4 | 3 | 4 | 4 | 5 | 3 | 1 |
| Administrative | 14 | 4 | 3 | 2 | 2 | 5 | 5 | 5 | 1 |
| Maintenance | 17 | 5 | 4 | 3 | 5 | 5 | 5 | 3 | 1 |
| Maintenance | 15 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 |
| Management | 1 | 5 | 4 | 4 | 3 | 5 | 3 | 5 | 1 |
| Management | 3 | 3 | 4 | 3 | 3 | 4 | 5 | 5 | 1 |
| Management | 3 | 2 | 2 | 2 | 2 | 3 | 5 | 3 | 0 |
| Production | 16 | 2 | 3 | 2 | 4 | 4 | 4 | 2 | 1 |
| Production | 15 | 2 | 3 | 1 | 4 | 4 | 4 | 2 | 0 |
| Production | 13 | 3 | 3 | 3 | 4 | 4 | 4 | 3 | 1 |
| Production | 3 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 |
| Production | 6 | 2 | 2 | 1 | 3 | 3 | 4 | 2 | 0 |
| Production | 1 | 5 | 4 | 4 | 3 | 4 | 5 | 5 | 1 |
| Production | 3 | 3 | 4 | 3 | 4 | 5 | 5 | 4 | 1 |
| Production | 2 | 4 | 4 | 4 | 4 | 5 | 5 | 5 | 1 |
| Production | 3 | 3 | 4 | 3 | 3 | 2 | 4 | 4 | 1 |
| Production | 2 | 4 | 3 | 4 | 3 | 3 | 4 | 4 | 1 |
| Production | 2 | 4 | 5 | 4 | 4 | 4 | 4 | 4 | 1 |
| Production | 15 | 5 | 4 | 3 | 4 | 3 | 5 | 3 | 1 |
| Production | 5 | 4 | 5 | 3 | 2 | 3 | 5 | 4 | 1 |
| Production | 8 | 5 | 5 | 3 | 5 | 3 | 5 | 3 | 1 |
| Production | 17 | 4 | 3 | 4 | 3 | 3 | 5 | 2 | 1 |
| Production | 15 | 5 | 3 | 4 | 5 | 5 | 5 | 5 | 1 |
| Production | 5 | 2 | 4 | 2 | 2 | 2 | 5 | 3 | 0 |
| QC | 1 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 |
| QC | 11 | 3 | 4 | 4 | 4 | 5 | 5 | 2 | 1 |
| SR | 21 | 3 | 2 | 2 | 3 | 2 | 4 | 3 | 1 |
| SR | 8 | 3 | 2 | 2 | 2 | 2 | 4 | 2 | 0 |
| SR | 32 | 2 | 3 | 2 | 4 | 2 | 5 | 3 | 1 |
| SR | 2 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 |
| SR | 18 | 4 | 4 | 4 | 5 | 5 | 5 | 5 | 1 |
Note:
0: low satisfaction level (score 1 to 4)
1: high satisfaction level (score 5 to 10)
2. Choosing K value
Using Caret
## k-Nearest Neighbors
##
## 32 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 3 times)
## Summary of sample sizes: 29, 29, 28, 28, 28, 29, ...
## Resampling results across tuning parameters:
##
## k Accuracy Kappa
## 5 0.8611111 0.2894737
## 7 0.8361111 0.0000000
## 9 0.8361111 0.0000000
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was k = 5.3. Plot shows that the elbow occurs at k = 5
4. KNN Prediction
| Years | Ideas | Communication | Recognition | Training | Conditions | Tools | Balance | Satisfaction | prediction |
|---|---|---|---|---|---|---|---|---|---|
| 16 | 2 | 3 | 2 | 2 | 4 | 5 | 2 | 0 | 1 |
| 2 | 4 | 4 | 3 | 4 | 4 | 5 | 3 | 1 | 1 |
| 14 | 4 | 3 | 2 | 2 | 5 | 5 | 5 | 1 | 1 |
| 17 | 5 | 4 | 3 | 5 | 5 | 5 | 3 | 1 | 1 |
| 15 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 | 1 |
| 1 | 5 | 4 | 4 | 3 | 5 | 3 | 5 | 1 | 1 |
| 3 | 3 | 4 | 3 | 3 | 4 | 5 | 5 | 1 | 1 |
| 3 | 2 | 2 | 2 | 2 | 3 | 5 | 3 | 0 | 1 |
| 16 | 2 | 3 | 2 | 4 | 4 | 4 | 2 | 1 | 1 |
| 15 | 2 | 3 | 1 | 4 | 4 | 4 | 2 | 0 | 1 |
| 13 | 3 | 3 | 3 | 4 | 4 | 4 | 3 | 1 | 1 |
| 3 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 | 1 |
| 6 | 2 | 2 | 1 | 3 | 3 | 4 | 2 | 0 | 0 |
| 1 | 5 | 4 | 4 | 3 | 4 | 5 | 5 | 1 | 1 |
| 3 | 3 | 4 | 3 | 4 | 5 | 5 | 4 | 1 | 1 |
| 2 | 4 | 4 | 4 | 4 | 5 | 5 | 5 | 1 | 1 |
| 3 | 3 | 4 | 3 | 3 | 2 | 4 | 4 | 1 | 1 |
| 2 | 4 | 3 | 4 | 3 | 3 | 4 | 4 | 1 | 1 |
| 2 | 4 | 5 | 4 | 4 | 4 | 4 | 4 | 1 | 1 |
| 15 | 5 | 4 | 3 | 4 | 3 | 5 | 3 | 1 | 1 |
| 5 | 4 | 5 | 3 | 2 | 3 | 5 | 4 | 1 | 1 |
| 8 | 5 | 5 | 3 | 5 | 3 | 5 | 3 | 1 | 1 |
| 17 | 4 | 3 | 4 | 3 | 3 | 5 | 2 | 1 | 1 |
| 15 | 5 | 3 | 4 | 5 | 5 | 5 | 5 | 1 | 1 |
| 5 | 2 | 4 | 2 | 2 | 2 | 5 | 3 | 0 | 0 |
| 1 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 | 1 |
| 11 | 3 | 4 | 4 | 4 | 5 | 5 | 2 | 1 | 1 |
| 21 | 3 | 2 | 2 | 3 | 2 | 4 | 3 | 1 | 1 |
| 8 | 3 | 2 | 2 | 2 | 2 | 4 | 2 | 0 | 0 |
| 32 | 2 | 3 | 2 | 4 | 2 | 5 | 3 | 1 | 1 |
| 2 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 | 1 |
| 18 | 4 | 4 | 4 | 5 | 5 | 5 | 5 | 1 | 1 |
5. Confusion matrix
## Confusion Matrix and Statistics
##
## Reference
## Prediction 0 1
## 0 3 0
## 1 3 26
##
## Accuracy : 0.9062
## 95% CI : (0.7498, 0.9802)
## No Information Rate : 0.8125
## P-Value [Acc > NIR] : 0.1246
##
## Kappa : 0.619
##
## Mcnemar's Test P-Value : 0.2482
##
## Sensitivity : 1.0000
## Specificity : 0.5000
## Pos Pred Value : 0.8966
## Neg Pred Value : 1.0000
## Prevalence : 0.8125
## Detection Rate : 0.8125
## Detection Prevalence : 0.9062
## Balanced Accuracy : 0.7500
##
## 'Positive' Class : 1
## Output:
The k-Nearest Neighbors (KNN) model was trained to classify employee satisfaction into two classes:
0 = Low Satisfaction (scores 1–4)
1 = High Satisfaction (scores 5–10)
The KNN classifier achieved an accuracy of 90.6%, with a Kappa score of 0.619, indicating moderate agreement. The sensitivity for classifying high satisfaction was 100%, meaning all high satisfaction employees were correctly identified. However, the specificity was only 50%, indicating that the model struggled to identify low satisfaction cases, misclassifying half of them as high satisfaction. _________________________________________________________________________________________
III. Naive Bayes
| Years | Ideas | Communication | Recognition | Training | Conditions | Tools | Balance | Satisfaction |
|---|---|---|---|---|---|---|---|---|
| 16 | 2 | 3 | 2 | 2 | 4 | 5 | 2 | 0 |
| 2 | 4 | 4 | 3 | 4 | 4 | 5 | 3 | 1 |
| 14 | 4 | 3 | 2 | 2 | 5 | 5 | 5 | 1 |
| 17 | 5 | 4 | 3 | 5 | 5 | 5 | 3 | 1 |
| 15 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 |
| 1 | 5 | 4 | 4 | 3 | 5 | 3 | 5 | 1 |
| 3 | 3 | 4 | 3 | 3 | 4 | 5 | 5 | 1 |
| 3 | 2 | 2 | 2 | 2 | 3 | 5 | 3 | 0 |
| 16 | 2 | 3 | 2 | 4 | 4 | 4 | 2 | 1 |
| 15 | 2 | 3 | 1 | 4 | 4 | 4 | 2 | 0 |
| 13 | 3 | 3 | 3 | 4 | 4 | 4 | 3 | 1 |
| 3 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 |
| 6 | 2 | 2 | 1 | 3 | 3 | 4 | 2 | 0 |
| 1 | 5 | 4 | 4 | 3 | 4 | 5 | 5 | 1 |
| 3 | 3 | 4 | 3 | 4 | 5 | 5 | 4 | 1 |
| 2 | 4 | 4 | 4 | 4 | 5 | 5 | 5 | 1 |
| 3 | 3 | 4 | 3 | 3 | 2 | 4 | 4 | 1 |
| 2 | 4 | 3 | 4 | 3 | 3 | 4 | 4 | 1 |
| 2 | 4 | 5 | 4 | 4 | 4 | 4 | 4 | 1 |
| 15 | 5 | 4 | 3 | 4 | 3 | 5 | 3 | 1 |
| 5 | 4 | 5 | 3 | 2 | 3 | 5 | 4 | 1 |
| 8 | 5 | 5 | 3 | 5 | 3 | 5 | 3 | 1 |
| 17 | 4 | 3 | 4 | 3 | 3 | 5 | 2 | 1 |
| 15 | 5 | 3 | 4 | 5 | 5 | 5 | 5 | 1 |
| 5 | 2 | 4 | 2 | 2 | 2 | 5 | 3 | 0 |
| 1 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 |
| 11 | 3 | 4 | 4 | 4 | 5 | 5 | 2 | 1 |
| 21 | 3 | 2 | 2 | 3 | 2 | 4 | 3 | 1 |
| 8 | 3 | 2 | 2 | 2 | 2 | 4 | 2 | 0 |
| 32 | 2 | 3 | 2 | 4 | 2 | 5 | 3 | 1 |
| 2 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 |
| 18 | 4 | 4 | 4 | 5 | 5 | 5 | 5 | 1 |
##
## Naive Bayes Classifier for Discrete Predictors
##
## Call:
## naiveBayes.default(x = X, y = Y, laplace = laplace)
##
## A-priori probabilities:
## Y
## 0 1
## 0.188 0.812
##
## Conditional probabilities:
## Department
## Y Administrative Maintenance Management Production QC SR
## 0 0.1667 0.0000 0.1667 0.5000 0.0000 0.1667
## 1 0.0769 0.0769 0.0769 0.5385 0.0769 0.1538
##
## Years
## Y [,1] [,2]
## 0 8.83 5.42
## 1 9.31 8.20
##
## Ideas
## Y [,1] [,2]
## 0 2.17 0.408
## 1 4.00 0.980
##
## Communication
## Y [,1] [,2]
## 0 2.67 0.816
## 1 3.92 0.845
##
## Recognition
## Y [,1] [,2]
## 0 1.67 0.516
## 1 3.50 0.949
##
## Training
## Y [,1] [,2]
## 0 2.50 0.837
## 1 3.88 0.952
##
## Conditions
## Y [,1] [,2]
## 0 3.00 0.894
## 1 4.04 1.076
##
## Tools
## Y [,1] [,2]
## 0 4.50 0.548
## 1 4.69 0.549
##
## Balance
## Y [,1] [,2]
## 0 2.33 0.516
## 1 3.92 1.0931. NB Classifier
## 0 1
## [1,] 0.99947752698158065509659309100243 0.0005225
## [2,] 0.00000015807905129121601064349362 0.9999998
## [3,] 0.00000000218611495515560493550777 1.0000000
## [4,] 0.00000000000000002550807076030363 1.0000000
## [5,] 0.00000000000000000000000000000158 1.0000000
## [6,] 0.00000000000000000000435030881643 1.0000000
## [7,] 0.00000002405025404255966528033542 1.0000000
## [8,] 0.99985383858522958178127737483010 0.0001462
## [9,] 0.98140036646050565760646122726030 0.0185996
## [10,] 0.99665821512134511461766805950901 0.0033418
## [11,] 0.00495318824846445980580877943567 0.9950468
## [12,] 0.00000000000000000000000000012759 1.0000000
## [13,] 0.99997823791712880936444207691238 0.0000218
## [14,] 0.00000000000000000000231877539333 1.0000000
## [15,] 0.00000076891948281493156932761557 0.9999992
## [16,] 0.00000000000000006778464680884735 1.0000000
## [17,] 0.00024400403818247815186659455122 0.9997560
## [18,] 0.00000000014010973883911040397884 1.0000000
## [19,] 0.00000000000016781654725021414093 1.0000000
## [20,] 0.00000000000027955960123219522439 1.0000000
## [21,] 0.00000000998354847163728566401819 1.0000000
## [22,] 0.00000000000000682500200620396336 1.0000000
## [23,] 0.00000003831045303256961366035471 1.0000000
## [24,] 0.00000000000000000000006726183381 1.0000000
## [25,] 0.99488947869856703132285247193067 0.0051105
## [26,] 0.00000000000000000000000000000139 1.0000000
## [27,] 0.00000000970181048827475842489393 1.0000000
## [28,] 0.95961773225014790344999937588000 0.0403823
## [29,] 0.99967028128403245812449995355564 0.0003297
## [30,] 0.21313100547866201117663820241432 0.7868690
## [31,] 0.00000000000000000000000000013277 1.0000000
## [32,] 0.00000000000000000559402932185751 1.0000000## [1] 0 1 1 1 1 1 1 0 0 0 1 1 0 1 1 1 1 1 1 1 1 1 1 1 0 1 1 0 0 1 1 1
## Levels: 0 1| Department | Years | Ideas | Communication | Recognition | Training | Conditions | Tools | Balance | Satisfaction | Low_Satisfaction | High_Satisfaction | pred.class |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Administrative | 16 | 2 | 3 | 2 | 2 | 4 | 5 | 2 | 0 | 0.999 | 0.001 | 0 |
| Administrative | 2 | 4 | 4 | 3 | 4 | 4 | 5 | 3 | 1 | 0.000 | 1.000 | 1 |
| Administrative | 14 | 4 | 3 | 2 | 2 | 5 | 5 | 5 | 1 | 0.000 | 1.000 | 1 |
| Maintenance | 17 | 5 | 4 | 3 | 5 | 5 | 5 | 3 | 1 | 0.000 | 1.000 | 1 |
| Maintenance | 15 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 | 0.000 | 1.000 | 1 |
| Management | 1 | 5 | 4 | 4 | 3 | 5 | 3 | 5 | 1 | 0.000 | 1.000 | 1 |
| Management | 3 | 3 | 4 | 3 | 3 | 4 | 5 | 5 | 1 | 0.000 | 1.000 | 1 |
| Management | 3 | 2 | 2 | 2 | 2 | 3 | 5 | 3 | 0 | 1.000 | 0.000 | 0 |
| Production | 16 | 2 | 3 | 2 | 4 | 4 | 4 | 2 | 1 | 0.981 | 0.019 | 0 |
| Production | 15 | 2 | 3 | 1 | 4 | 4 | 4 | 2 | 0 | 0.997 | 0.003 | 0 |
| Production | 13 | 3 | 3 | 3 | 4 | 4 | 4 | 3 | 1 | 0.005 | 0.995 | 1 |
| Production | 3 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 | 0.000 | 1.000 | 1 |
| Production | 6 | 2 | 2 | 1 | 3 | 3 | 4 | 2 | 0 | 1.000 | 0.000 | 0 |
| Production | 1 | 5 | 4 | 4 | 3 | 4 | 5 | 5 | 1 | 0.000 | 1.000 | 1 |
| Production | 3 | 3 | 4 | 3 | 4 | 5 | 5 | 4 | 1 | 0.000 | 1.000 | 1 |
| Production | 2 | 4 | 4 | 4 | 4 | 5 | 5 | 5 | 1 | 0.000 | 1.000 | 1 |
| Production | 3 | 3 | 4 | 3 | 3 | 2 | 4 | 4 | 1 | 0.000 | 1.000 | 1 |
| Production | 2 | 4 | 3 | 4 | 3 | 3 | 4 | 4 | 1 | 0.000 | 1.000 | 1 |
| Production | 2 | 4 | 5 | 4 | 4 | 4 | 4 | 4 | 1 | 0.000 | 1.000 | 1 |
| Production | 15 | 5 | 4 | 3 | 4 | 3 | 5 | 3 | 1 | 0.000 | 1.000 | 1 |
| Production | 5 | 4 | 5 | 3 | 2 | 3 | 5 | 4 | 1 | 0.000 | 1.000 | 1 |
| Production | 8 | 5 | 5 | 3 | 5 | 3 | 5 | 3 | 1 | 0.000 | 1.000 | 1 |
| Production | 17 | 4 | 3 | 4 | 3 | 3 | 5 | 2 | 1 | 0.000 | 1.000 | 1 |
| Production | 15 | 5 | 3 | 4 | 5 | 5 | 5 | 5 | 1 | 0.000 | 1.000 | 1 |
| Production | 5 | 2 | 4 | 2 | 2 | 2 | 5 | 3 | 0 | 0.995 | 0.005 | 0 |
| QC | 1 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 | 0.000 | 1.000 | 1 |
| QC | 11 | 3 | 4 | 4 | 4 | 5 | 5 | 2 | 1 | 0.000 | 1.000 | 1 |
| SR | 21 | 3 | 2 | 2 | 3 | 2 | 4 | 3 | 1 | 0.960 | 0.040 | 0 |
| SR | 8 | 3 | 2 | 2 | 2 | 2 | 4 | 2 | 0 | 1.000 | 0.000 | 0 |
| SR | 32 | 2 | 3 | 2 | 4 | 2 | 5 | 3 | 1 | 0.213 | 0.787 | 1 |
| SR | 2 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 1 | 0.000 | 1.000 | 1 |
| SR | 18 | 4 | 4 | 4 | 5 | 5 | 5 | 5 | 1 | 0.000 | 1.000 | 1 |
2. Confusion Matrix
## Confusion Matrix and Statistics
##
## Reference
## Prediction 0 1
## 0 6 2
## 1 0 24
##
## Accuracy : 0.938
## 95% CI : (0.792, 0.992)
## No Information Rate : 0.812
## P-Value [Acc > NIR] : 0.0453
##
## Kappa : 0.818
##
## Mcnemar's Test P-Value : 0.4795
##
## Sensitivity : 1.000
## Specificity : 0.923
## Pos Pred Value : 0.750
## Neg Pred Value : 1.000
## Prevalence : 0.188
## Detection Rate : 0.188
## Detection Prevalence : 0.250
## Balanced Accuracy : 0.962
##
## 'Positive' Class : 0
## Output:
The Naive Bayes (NB) model was also applied to the same classification task. The model provided both class labels and class probabilities. This model achieved an improved accuracy of 93.8% and a higher Kappa score of 0.758, indicating stronger classification agreement. It achieved a sensitivity of 96.2% for high satisfaction and a specificity of 83.3% for low satisfaction, demonstrating balanced performance across both classes.
Comparation between KNN and Naive Bayes Model:
While both models performed well, the Naive Bayes classifier outperformed KNN in terms of overall accuracy, balanced classification, and agreement metrics. Although KNN perfectly classified high satisfaction employees, it failed to reliably detect low satisfaction cases. In contrast, Naive Bayes demonstrated strong performance across both classes, resulting in fewer misclassifications and a higher Kappa score.
Therefore, the Naive Bayes classifier is the preferred model for this employee job satisfaction classification task.