Internet load balancing algorithms can be categorised into static and dynamic algorithms. Static algorithms like Round Robin and IP hash are rule based and do not take into account dynamic information like load on individual servers. Dynamic algorithms like Least connections take this into account and aim to distribute traffic more optimally, but lead to requirement of monitors or polling mechanisms to obtain this information. Predictive load balancing algorithms aim to remove this requirement by trying to predict load induced on servers due to requests rather than measuring it directly. We aim to provide an improved implementation of algorithm described by Patil et al.[1] and compare this implementation with a static algorithm like Round Robin in terms of performance and resource utilisation. This implementation is for a web application which does text-to-speech synthesis.