ABSTARCT :
Using a novel approach with video-recordings of sales interactions, this study focuses on a dynamic analysis of salesperson effectiveness in handling customer queries. We conceptualize salesperson behaviors, namely, resolving, relating, and emoting, as separate elements of customer query handling and empirically identify the distinct verbal and nonverbal cues that salespeople use to display these behaviors during sales interactions. We draw from compensation effects in social cognition theory to propose that customers’ perceptions of a salesperson’s effectiveness are prone to trade-offs between competence (resolving behaviors) and warmth (relating and emoting behaviors). Results, robust to endogeneity corrections, support the proposed tradeoffs such that the effectiveness of salesperson’s resolving behavior is significantly curtailed, even neutralized, by the salesperson’s relating and emoting behaviors. We situate these counterintuitive results within the extant theory and research on sales interactions, and outline implications for practice.
EXISTING SYSTEM :
? The query understanding of conversational search in E-commerce is of great difference with the natural language understanding in task-oriented dialog system.
? If slot filling is applied, large amount of semantic slots should be defined to cover all product properties, e.g. brand, color, size, style, skirt length and so on, and it is an expensive manual work.
? In task-oriented dialog systems, natural language understanding mainly composes of two components: slot filling and dialog state tracking.
? It is noteworthy that queries in E-commerce search commonly only contain several unordered keywords that describe some key properties of user’s needed products so as the internal query.
DISADVANTAGE :
? Customers seek both specificity and clarity from the salesperson’s response: specificity to process the potentially unique question the customer has, and clarity to provide a response that helps resolve or reframe the underlying issues.
? However, some studies also report opposite, less functional effects of relating behaviors, especially in non-routine or problem-related contexts.
? Customer queries are deliberate attempts on the part of the customer to control and direct the sales communications toward issues and concerns that address their decision uncertainty.
? At the start of a sales interaction, the customer likely has limited knowledge and thus issues basic and general queries.
PROPOSED SYSTEM :
• We also propose a self attention based neural network to handle the task in a machine comprehension perspective.
• To handle this task, we involve a machine comprehension perspective, and propose a neural network based query tracking model.
• In query tracking, we propose to leverage self attention based encoder as a more suitable substitute.
• In our model, we update the internal query without the help of slot, and turn the problem to a word-level binary classification.
• We propose a novel neural network model based on machine comprehension perspective.
ADVANTAGE :
? Prior studies tend to use dependent variables that reflect desired sales outcomes including customer satisfaction and sales performance.
? Adaptive confidence acts as an antecedent of adaptive behaviors, which affect the salesperson’s outcome performance.
? There is a positive relationship among listening behavior and adaptive selling, sales performance, and job satisfaction.
? This evidence confirms that customers continuously monitor salespeople’s efficacy in handling their queries and weigh resolving behaviors more heavily at later stages (when the queries are more significant and specific) compared with earlier stages (when queries are basic and broad).
|