Adopting AI in financial advisory is a challenging task as there exists multiple sources of information to digest and interpret. Such information consumption process are very lengthy for financial advisors, reducing the efficiency and timeliness for their advice and recommendation given to their clients. In this work, we introduce a multi-step framework that consumes and combines news and industry-focused fund research analyst report to assist in fund recommendation process using Large Language Models (LLMs). To quantitatively evaluate the efficacy of the approach, we track the weekly and monthly market performance of representative industry-focused fund after news and report released date, and compute a Normalized Discounted Cumulative Gain (NDCG) score between the rankings of the fund performance and recommendation rating scores. We find that utilizing analyst report and self consistency in the framework increase the NDCG score from 0.72 to 0.93 comparing to consuming news only without self consistency, based on the time frame of our experimental evaluation.