1. INTRODUCTIONThe project shown here is related to our daily life where we have to buy things and we have constraints with us, that is, with given money constraints we have to manage our budget effectively. The project includes a buyer, who must invest his money to purchase items. Each item is associated with a price and also has a margin. Margin indicates the profit the buyer gets when selling that item. This is quite similar to the backpack problem where we have the weight of the backpack and the items with their weight and associated profit value. By relating this app to the backpack, here the weight of the bag is considered as the total money the buyer has and the weight of the items related to the price of the item and the value in the backpack is related to the profit margin. The knapsack problem is an NP problem, which means it cannot be solved in polynomial time, so the project uses a genetic algorithm to implement it. There are concrete examples where we can implement this application, for example. • In a stationery store, we have many stationery items like pens, pencils, notebooks and many more. So how should a trader decide to keep items in the store that will bring him maximum profit when he has little money to buy things. • In the canteen or any other eating place, there are many items like burgers, sandwiches, cold drinks, etc. so how to select items on a limited budget can be done with this app. For future work using self-learning techniques, we will improve the application. Learning will yield better results and the most appropriate solutions.2. LITERATURE SURVEY2.1 Knapsack 0/1 PROBLEMThe knapsack 0/1 problem is a combi...... middle of paper ......e local optima. A few researchers have used diversity measures to control the search direction of evolutionary algorithms. By mixing adaptive crossover and mutation with diversity-guided mutation and modifying adaptive crossover strategies, an adaptive genetic algorithm with diversity-guided mutation (MHAGA) was developed [8]. There is evidence that AGADM will converge to the optimal world, but (AGA) does not always do so. AGADM to solve the 0-1 knapsack problem and use the greedy transformation algorithm to repair an infeasible solution and the problem of insufficient knapsack resource utilization. therefore, AGADM is based on a greedy algorithm (named Modified Hybrid Adaptive Genetic Algorithm, MHAGA).2.3.5 MODIFIED ADAPTIVE OPERATORSCrossing and mutation is the key that affects the behavior and performance of GA. Adaptive probabilities of crossing and mutation of individuals (noted