Limitations of apriori algorithm

What are the limitations of apriori? So each pass requires large number of disk reads. GB database stored in hard disk with block size 8KB require roughly 120block reads for a single pass. I would answer in terms of space and time complexity.

Let us say that number of input transactions are N(=20) and the number of unique elements be R(approx 900).

At times, you need a large number of candidate rules. It can become computationally expensive. It is also an expensive method to calculate support because the calculation has to go through the entire database.

Apriori Algorithm – Pros. The overall performance can be reduced as it scans the database for multiple times. The time complexity and space complexity of the apriori algorithm is O (D), which is very high.

Here D represents the horizontal width present in the database.

You can address this issue by evaluating obtained rules on the held-out test data for the support, confidence, lift, and conviction values. It uses a bottom-up approach, designed for finding Association rules in a database that contains transactions. Easy to implement 2. By Annalyn Ng , Ministry of Defence of Singapore.

Put simply, the apriori principle states that if an itemset is infrequent, then all its subsets must also be infrequent. The apriori algorithm works slow compared to other algorithms. Finding large no of candidate rules as well as evaluating support tends out to be computationally expensive.

The main limitation is costly wasting of time to hold a vast number of candidate sets with much frequent itemsets, low minimum support or large itemsets. All infrequent itemsets can be pruned if it has an infrequent subset. Advantages of FP growth algorithm :- 1. Faster than apriori algorithm 2. No candidate generation 3. Only two passes over dataset Disadvantages of FP growth algorithm :- 1. FP tree may not fit in memory 2. For example, if the transaction DB has 1frequent 1-itemsets, they will generate 1candidate 2-itemsets even after employing the downward closure.

Limitation of apriori algo Needs several iterations of the data Uses a uniform minimum support threshold Difficulties to find. Continue reading to learn more! To generate the candidate set it requires multiple scan over the database. Practically its complexity can be significantly reduced using pruning process in intermediate steps and using some optimizations techniques like usage of hash tress for calculating support values of candidates, still theoretically its time complexity is O (d) where d is total number of unique items in your transaction dataset.

Most ML algorithms in DS work. The two most relevant limitations are that it generates a large number of subsets and that its breadth first traversing strategy takes a very long time to traverse the entire database. It also withdraws rescanning the database. The various variations we discussed are DHP, Partition, DIC and Sampling algorithms.

The algorithm gets dismissed when various itemsets cannot be prolonged further. We also studied their comparisons. With the quick growth in e-commerce applications, there is an accumulation vast quantity of data in months not in years.

Data Mining, also known as Knowledge Discovery in Databases(KDD), to find anomalies, correlations, patterns, and trends to predict outcomes.