Web caching is a mechanism used to improve network performance by reducing network traffic, load on the Web Server and delay in accessing the Web page. This is achieved by storing frequently accessed Web pages on proxy cache placed within the network. Caching can be taken place either at client side or in the proxy Server. Web proxy cache can potentially improve network performance by reducing the number of requests that reaches the server, the volume of data transferred through the network and the delay in accessing Web page. When a requested page is not present in the cache and cache is full then removal of one or more cached documents take pace. The performance of proxy depends on page replacement algorithm. The decision by which document is evicted from the cache is depends on different kinds of replacement policies used. A number of exiting cache replacement algorithms, which attempt to reduce various cost metrics such as hit rate, byte hit rate, average latency and total cost. In this paper presents one such technique that improves the Web cache performance by modifying Least Frequently Used (LFU) algorithm. Proposed algorithm is based on recency, frequency and popularity of web page with the help of Web usage mining.