top of page

COLLEGE CAMPUS RECRUITER

Every student has goals to work at their dream company. MBA students have specific expertise in respective fields such as Sales, marketing, finance, and banking. They target specific companies and make their profile accordingly to increase their selection chances. But there is something that they lag, and that is an accurate predictor. This project can build an eco-system where companies can get the best candidates, students can land a job at their desired organization, and colleges can increase their placement ratios.

campus placement.jpg

This project aims to predict whether the candidate will get the job or not according to the profile. It analyses the past students’ data, and can make accurate predictions about current students.

This project considers 15 different factors for analysis of placements.

sl_no – serial number

gender - Male / Female

ssc_p – 10th percentile

ssc_b – 10th board

hsc_p - 12th percentile

hsc_b - 12th board

hsc_s - 12th stream (Science/ Commerce/ Arts)

degree_p – degree percentile

degree_t – degree major

workex - previous work experience

etest_p - estimated percentage in masters

specialization – specialized courses

mba_p – MBA performance

status - Placed / not placed

salary

The graph below displays the data of average salary.

Prediction models: These models are used for the predictions of campus placements.

1. Logistic regression

2. Decision Tree

3. Random Forest

Logistic Regression

Code:

import warnings

warnings.filterwarnings('ignore')

from sklearn.linear_model import LogisticRegression

from sklearn import metrics

logreg= LogisticRegression()

logreg.fit(X_train, y_train)

y_pred =logreg.predict(X_test)

print(logreg.score(X_test, y_test))

Accuracy achieved in predictions: 83.334%

===============================================

Decision Tree

Code:

from sklearn.tree import DecisionTreeClassifier

dt=DecisionTreeClassifier(criterion='gini',max_depth =3) #hyperparameter tuning

dt=dt.fit(X_train, y_train)

y_pred=dt.predict(X_test)

print('acuuracy==', metrics.accuracy_score(y_test, y_pred))

Accuracy achieved in predictions: 73.81%

===============================================

Random Forest

Code:

from sklearn.ensemble import RandomForestClassifier

rt = RandomForestClassifier(n_estimators=100)

rt.fit(X_train , y_train)

y_pred =rt.predict(X_test)

print('acuuracy==', metrics.accuracy_score(y_test, y_pred))

Accuracy achieved in predictions: 80.95%

===============================================

bottom of page