Marketing strategies using unstructured data

Abstract

Managerial importance of marketing strategies necessitates a precise and reliable framework which transforms mere collection of data into meaningful values. This enables firms to define various product or brand attributes and effectively utilize them in strategic decision making. This dissertation focuses on quantifying product and brand attributes, where less attention was paid in empirical studies due to difficulties involved in quantifying them. Measurements of product design and brand relatedness is proposed in particular, utilizing car image and web query volume data, respectively. These measurements are incorporated into marketing strategies accordingly and provide interdisciplinary solutions to the issue of collaboration between design and marketing, and brand crisis management. The first study provide product design quantification method and its applications on marketing problems. With the quantified design similarities firms’ design repositioning strategies toward an ideal point is illustrated by projecting the proportion of variation in sales unexplained by non-design factors onto product design space. Information on desired market position and firms’ relative positions in design can be utilized to guide firms’ decisions, such as which design appeals more to consumers and boost sales. Research scope of the strategic issue of positioning is extended to the product design domain by providing measurable definitions of design for positioning and directions for design repositioning. In the second study, co-query volumes of brands are utilized as relatedness measurement to understand the market structure and demonstrate the usefulness of brand relatedness via a real-world case. Using brand relatedness measurement obtained using data from Google Trends, the market structure of the automobile industry is presented to reveal its competitive landscape. The relatedness with brands involved in product-harm crisis is further incorporated in empirical models to estimate the influence of crisis on future sales performance of each brand. This study contributes to the literature by clarifying the concept of brand relatedness and proposing a measure with readily accessible data.