Which model will be a good fit for your data ?

In this article we will explain the advantages and disadvantages of each machine learning model and which model will be a good fit for your data,the article is presented in a way that is easy to understand.

Linear Regression

1. The advantages

• Simple to implement and efficient to train.
• Overfitting can be reduced by regularization.
• Performs wellwhen the dataset is lenearly separable

2. The disadvantages

• Assumes that the data is independent which is rare in real life.
• Prone to noise and overfitting.
• Sensitive to outliers.

Logistic Regression

1. The advantages

• Less prone to overfitting but it can overfit in high dimensional datasets.
• Efficient when the dataset has features that are linearly separable.
• Easy to implement and efficient to train.

2. The disadvantages

• Should not be used when the number of observations are lesser than the number of features.
• Assumption of linearity which is rare in practise.
• Can only be used to predict discrete functions.

Support Vector Machine (SVM)

1. The advantages

• Good at hight dimensional data.
• Can work on small dataset.
• Can solve non-linear problems.

2. The disadvantages

• Inefficient on large data.
• Requires picking the right kernel

Decision Tree

1. The advantages

• Can work on high-dimensional data with excellent accuracy.
• Can solve non-linear problems.
• Easy to visualize and explain.

2. The disadvantages

• Overfitting Might be resolved by random forest.
• A small change in the data can lead to a large change in the structure of the optimal decision tree.
• Calculations can get very complex.

K Nearest Neighbour

1. The advantages

• Can make predictions without training.
• Time complexity is O(n).
• Can be used for both classification and regression.

2. The disadvantages

• Does not work well with large dataset.
• Sensitive to noisy data, missing values and outliers.
• Need feature scaling.
• Choose the correct K value.

Principal Component Analysis

1. The advantages

• Reduce correlated features.
• Reduce overfitting.

2. The disadvantages

• Principal components are less interpretable.
• Information loss.
• Must standardize data before implementing PCA.

Naive Bayes

1. The advantages

• Training period is less.
• Better suited for categorical inputs.
• Easy to implement.

2. The disadvantages

• Assumes that all features are independent which is rarely happening in real life.
• Zero Frequency.
• Estimations can be wrong in some cases.

ANN (Artificial Neural Network)

1. The advantages

• Have fault tolerance.
• Have the ability to learn and model non-linear and complex relationships.
• Can generalize on unsean data.

2. The disadvantages

• Long training time.
• Non-guaranteed convergence.
• Black box.
• Hard to explain the solution.
• Hardware dependence.
• Requires user’s ability to translate the problem.

Adaboost

1. The advantages

• Relatively robust to overfitting.
• High accuracy.
• Easy to understand and to visualize.

2. The disadvantages

• Sensitive to noise data.
• Affected by outliers.
• Not optimized for speed.