Frequent itemset mining is one of the most necessary problems in data extraction. The chance of devious a discrepancy private frequent itemset mining algorithm which can not only accomplish high data usefulness and a high level of secrecy, but also offer high time effectiveness. To this end, offer a discrepancy frequent itemset mining algorithm based on the Frequent Pattern-growth algorithm, which is referred to as Private Frequent Pattern-growth. The Private frequent Pattern -growth algorithm consists of a preprocessing phase and a mining phase. To improve the utility and secrecy tradeoff, a innovative smart splitting method is proposed to change the database in preprocessing phase. It needs to be performed only once for a given database. To compensate the information loss caused by transaction splitting, To estimate the definite support of itemsets in the original database in mining segment utilize run time estimation method. In accumulation, develop a dynamic reduction method to dynamically reduce the amount of noise added to guarantee privacy during the extracting process by leveraging the downward closure property. Private common pattern-growth algorithm is shown it is ε-differentially private through formal privacy analysis; explain that  PFP-growth algorithm is ε- discrepancy secrecy. Extensive experiments on real datasets exemplify that our PFP-growth algorithm considerably outperforms the state-of-the-art techniques.