Consumption Behavior Prediction Based on Multiobjective Evolutionary Algorithm

Consumption behavior prediction reveals customer attributes, personal preferences, and intrinsic laws. Organizations would benefit from knowing further about needs business desires by monitoring client to provide more precise recommendations boost acquisition rates. The economics of the customer, buyer groupings, product quality are only a few numerous variables that influence behavior. key issue has be resolved at this time is how filter out useful information these vast amounts data forecast For consumption analysis with an advanced quantitative research process, we proposed multiobjective evolutionary algorithm, which significantly boosts accuracy predictions. dataset initially gathered based on consumer preferences behaviors as essential for entire model. Min-max normalization used component preprocessing get elimination redundant superfluous data. Word2vec model utilized feature extraction, boosted ant colony optimization (BACO) employed choose best features. Utilizing suggested algorithm (MOEA), predictions made. system’s performance assessed, metrics contrasted established methods. findings demonstrate MOEA technique performs well than traditional ML, XGB, AI, HNB methods in terms (95 percent), (97 precision (99 recall (93 F 1 -score (98 (50 seconds). Hence, outcomes show regression sustainable. system demonstrated its efficiency boosting profitability.