Data-Driven SEO Strategy Optimization to Enhance MSME Sales Performance on Indonesian E-Commerce Platforms

Abstract

The rapid growth of digital commerce in Indonesia has created both opportunities and challenges for Micro, Small, and Medium Enterprises (MSMEs) seeking to increase their online visibility and sales. This study presents a data-driven approach to Search Engine Optimization (SEO) strategy optimization aimed at enhancing MSME sales performance on leading Indonesian e-commerce platforms, including Tokopedia and Shopee. Using a quantitative design, the research integrates Microsoft Excel for preliminary data exploration and Google Colab (Python) for advanced analysis and predictive modeling. The dataset, comprising over 1,000 transaction entries, includes key SEO-related indicators such as keyword rank, website traffic, backlinks, social media engagement score, advertising spend, and monthly sales. Ensemble regression models—Random Forest and Gradient Boosting—were employed to evaluate the predictive relationship between SEO factors and sales outcomes, validated through RMSE and R² metrics. The findings indicate that advertising expenditure (r = +0.83), backlinks (+0.29), and social media engagement (+0.25) are the most influential predictors of sales performance, while website traffic shows a weaker positive correlation (+0.13). These results highlight the critical role of integrated SEO and digital advertising strategies in improving MSME competitiveness. The study demonstrates that accessible analytical tools can empower MSMEs to make data-driven marketing decisions. Future research should expand model generalization across industries and explore additional digital variables to improve predictive accuracy.