What is apriori algorithm?

AffiliatePal is reader-supported. When you buy through links on our site, we may earn an affiliate commission.



The Apriori algorithm is a popular data mining technique used for discovering frequent itemsets in a dataset. It is widely used in market basket analysis, where the goal is to identify associations between items that are frequently purchased together. By finding these associations, businesses can gain valuable insights into customer behavior and make informed decisions regarding product placement, promotions, and cross-selling strategies.

Understanding the Apriori Algorithm

The Apriori algorithm follows a simple principle: if an itemset is frequent, then all of its subsets must also be frequent. This principle is known as the “Apriori property.” The algorithm iteratively generates candidate itemsets of increasing length and checks their support, which is the frequency of occurrence in the dataset. The support of an itemset is compared against a user-defined minimum support threshold to determine its frequency.

The algorithm starts with single items and gradually builds larger itemsets by combining frequent itemsets from the previous iteration. It prunes the search space by using the Apriori property to eliminate itemsets that cannot be frequent based on the support of their subsets. This pruning process significantly reduces the computational complexity of the algorithm.

Algorithm Steps

The Apriori algorithm can be summarized in the following steps:

Step 1: Generating frequent 1-itemsets
The algorithm scans the dataset to count the occurrences of each item. Items that meet the minimum support threshold are considered frequent 1-itemsets.

Step 2: Generating frequent k-itemsets
Using the frequent (k-1)-itemsets from the previous iteration, the algorithm generates candidate k-itemsets by joining the frequent itemsets. It then scans the dataset to count the occurrences of these candidate itemsets. Again, only the itemsets that meet the minimum support threshold are considered frequent k-itemsets.

Step 3: Repeat until no more frequent itemsets are found
The algorithm continues generating candidate itemsets and counting their support until no more frequent itemsets can be found. Each iteration increases the length of the itemsets until the maximum length is reached or no more frequent itemsets can be generated.

Advantages and Limitations

The Apriori algorithm has several advantages that contribute to its popularity in data mining:

1. Simplicity: The algorithm is relatively easy to understand and implement, making it accessible to both researchers and practitioners.

2. Scalability: The Apriori algorithm can handle large datasets efficiently by pruning the search space and reducing the number of candidate itemsets.

3. Flexibility: The algorithm allows users to define the minimum support threshold, enabling them to control the level of granularity in identifying frequent itemsets.

However, the Apriori algorithm also has some limitations:

1. High memory usage: As the algorithm needs to store candidate itemsets and their support counts, it can consume a significant amount of memory, especially for datasets with a large number of unique items.

2. Computationally intensive: The algorithm requires multiple passes over the dataset and generates a large number of candidate itemsets, leading to high computational complexity.

3. Dependency on minimum support threshold: The quality of the discovered itemsets heavily relies on the selection of the minimum support threshold. Setting it too low may result in a large number of frequent itemsets, making it difficult to extract meaningful insights. Conversely, setting it too high may lead to the omission of potentially valuable associations.


The Apriori algorithm is a powerful technique for discovering frequent itemsets in a dataset. By leveraging the Apriori property, it efficiently identifies associations between items and provides valuable insights into customer behavior. While the algorithm has its limitations, its simplicity, scalability, and flexibility make it a popular choice for market basket analysis and other data mining tasks.


– Agrawal, R., Imielinski, T., & Swami, A. (1993). Mining association rules between sets of items in large databases. ACM SIGMOD Record, 22(2), 207-216.
– Han, J., Pei, J., & Yin, Y. (2000). Mining frequent patterns without candidate generation. ACM SIGMOD Record, 29(2), 1-12.