Research on Pattern Mining focuses on developing efficient algorithms and methodologies to discover meaningful patterns in large and complex datasets across diverse domains. Recent advancements include mining both positive and negative sequential patterns with gap constraints using algorithms like NSPG-Miner, identifying top-k periodic high-utility patterns through threshold-raising and utility co-occurrence strategies, and extracting average-utility sequential patterns with pruning and overestimation techniques as in HAUSP-PG. Additionally, low-utility sequential pattern mining methods such as LUSPM_e enhance scalability and efficiency. These innovations collectively aim to improve computational performance, reduce redundancy, and enable actionable insights from complex sequential and temporal data.