PROPOSED MARKETING MIX STRATEGY IN ORGANIC FERTILIZER TRADING COMPANY BY UTILIZING BIG DATA ANALYTICS (CASE STUDY : PT SIMCO TRIDATAMA)

• Main Author: Hadrian Deswandi J., Muhammad
• Format: Theses
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/80898
• Institution: Institut Teknologi Bandung

The agricultural industry plays a pivotal role in a country’s food security and sustainability. While fertilizer products are essential for providing nutrition to crops, in practice, the excessive use of chemical fertilizers can lead to detrimental effects on soil quality, including physical, chemical, and biological damage, ultimately reducing soil fertility. To address this concern, the adoption of organic fertilizers is promoted to enhance soil quality and nutrient content, aiming for a balanced approach in optimizing plant nutrition while minimizing the adverse impacts associated with the overuse of chemical fertilizers. The post-Covid shift in consumer behavior towards online purchasing has influenced the agricultural sector, with a notable surge in plant-related product sales on Tokopedia (a prominent E-Commerce platform in Indonesia). Supported by data on the number of millennial farmers in Indonesia who are technologically literate, there is an opportunity for companies in the agricultural sector to leverage Big Data generated by E-Commerce websites. PT Simco Tridatama as a trading company that usually operates in the Business-to-Business (B2B) sector has problems in determining the right marketing mix strategy for retail and e-commerce market penetration which has an impact on fluctuations in sales of organic fertilizer products. This research aims to improve the marketing mix strategy (4ps) of organic fertilizer through the application of Big Data Analytics employing a Knowledge Discovery in Database (KDD) framework. Data collection from E-Commerce is conducted using the Web Scraping method, followed by processing and Data Mining techniques such as Pivot Tables, K-Means, and Multidimensional Scaling (MDS). Interpretation of data from data mining results serves as a solution for formulating improvement strategies for the company