Compact Representation of Association Rule With Sequential Item Mapping Rendering Approach

Association rule mining are widely used to uncover meaningful insights from real-world datasets. However, the complex nature of transactional data, especially when identifying frequent item patterns, poses significant challenges. One key way to tackle these challenges is by improving how the algorithm represents item relationships. An efficient representation ensures the algorithm can traverse the structure effectively, enabling it to uncover all embedded transactional rules. To tackle this, we introduce Sequential Item Mapping Rendering (SIMRs), a novel framework that leverages succinct data structures to optimize the representation of item relationships. SIMRs organizes item relationships hierarchically by transaction levels and compresses them into a compact string format, expressed as <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N₁N₂</i> …. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N_i</i>. This structured approach allows for more efficient processing and storage of data. Additionally, SIMRs integrates the Boyer-Moore substring search algorithm, which further accelerates the item relationship construction process. Experimental evaluations demonstrate the effectiveness of SIMRs in reducing both memory usage and execution time. In comparison to traditional algorithms as well as improved, the proposed algorithm consistently delivers better performance. These results highlight its potential as a robust and efficient solution for frequent pattern mining, particularly in scenarios involving large and complex datasets.