Exploration and Analysis of Collaborative Matching Algorithm Empowering Large Data Fiscal Budget

Abstract

At present, many budget companies have realized high-level computerized accounting and have high-speed and advanced database management systems. In order to adapt to the growth of budget entity informatization, the financial department must improve its own financial budget level. Introduce information technology, and develop corresponding financial budget software to better perform its own financial calculation function. This paper explores and analyzes the full collaborative matching algorithm of enabling big data financial budget and builds a financial big data financial budget platform through offline and online data collection. Combined with the matching algorithm and linear regression prediction algorithm in data analysis, the financial data is analyzed in depth. Finally, the PSO-SA algorithm runs 10 rounds on the datasets with matching scales $d=10$ and 30, respectively. It is found that the fluctuation is large when $d=10$ and relatively stable when $d=30$ . When $d=10$ , the maximum value is 7.2354, and the minimum value is 6.9969. When $d=10$ , the maximum value is 26.6403, and the minimum value is 23.9599. It can be concluded that when $d=0$ , PSO-SA can obtain a relatively good matching scheme, but it is easy to fall into a local optimal solution. The superposition effect of “data + computing power + algorithm + scenario” can help enterprises make better decisions. Embed complex analysis into daily management and trading scenarios to build a financial empowerment platform. Make the increasingly complex work more automated and intelligent, and improve financial efficiency.