From the above information, it can be anticipated that the quantity and level ofrating positively affect the number of favorite marks.H3: Quantity and level of ratings positively affect
FOREIGN TRADE UNIVERSITY FACULTY OF ECONOMICS AND INTERNATIONAL BUSINESS BUSINESS ANALYTICS FACTORS AFFECTING THE NUMBER OF CUSTOMERS RATING A PRODUCT AS FAVOURITE IN SEPHORA COSMETIC STORES Class Instructor Group : VJPE205(GD1-HK1-2324).1 : Assoc Prof., PhD Nguyen Thi Thuy Vinh : PhD Pham Thi Cam Anh : 14 Ha Noi, October 2023 GROUP CONTRIBUTION Name Student ID Contribution Nguyễn Hạnh Hương 2114110143 20 Nguyễn Thị Minh Tâm 2114110271 20 Đặng Lê Hằng 2114110214 22 Nguyễn Minh Hợp 2112150070 19 Trần Lâm Nhi 2112150131 19 TABLE OF CONTENTS Abstract Introduction Literature review EDA 3.1 Dataset overview and Sampling technique .5 3.1.1 Dataset Description 3.1.2 Research Methodology 3.2 Variables details 3.2.1 Dependent vs Independent (visualization for each) 3.2.2 Descriptive Analysis 11 3.2.3 Correlation Analysis 12 Hypothesis Testing 13 4.1 Hypothesis proposed .13 4.2 Results Interpreting .14 4.3 Model Assessment 15 Recommendations 16 Conclusion 18 Appendix .20 References 21 Abstract Today, e-commerce platforms have revolutionized the way consumers access and interact with their favorite brands Sephora, a global powerhouse in the beauty and cosmetics industry, has seamlessly transitioned into the online sphere with its varied range of products, from skincare to make up and fragrances By analyzing 2484 samples from Sephora’s database, this comprehensive analysis serves as an exploration of its products’ performance online through defining the factors contributing to their popularity and to which extent, shedding light on not only the brand’s success but also offering valuable insights for businesses in the beauty and retail sectors By identifying and analyzing these factors, the research offers a foundation for future actions for Sephora to further improve its product and strengthen the brand love 1 Introduction In today’s digital age, the beauty and cosmetics industry has seen a significant shift towards e-commerce, with consumers relying on online platforms to discover, evaluate, and purchase products Sephora, a leading global beauty retailer, has established a substantial online presence, offering a vast range of beauty products from various brands Within this dynamic e-commerce environment, understanding the factors that influence consumer engagement, particularly the relationship between various product-related variables and the accumulation of love counts, which reflects consumers' emotional engagement to a product and even indicates their intention to purchase, is of paramount importance This data analysis report delves into the intricate web of variables associated with Sephora products and aims to uncover patterns, correlations, and insights related to the accumulation of love counts The variables under investigation include product price, consumer ratings, reviews, stock availability, etc By scrutinizing the relationships between these variables and the number of people who have marked a product as a favorite, we seek to provide insights into consumer preferences and behavior in the beauty e-commerce domain, from which to draw broader implications for businesses in enhancing user engagement and product popularity In this research, the authors adopt the qualitative approach, in particular the regression technique to analyze the dataset The paper’s main content includes a dataset overview and Sampling technique, variables details, hypothesis testing, recommendations, and conclusion It is also important to acknowledge the limitations of this report Firstly, the model may not capture all relevant factors influencing the dependent variables The analysis also assumes that the data is representative and that the identified relationships will remain consistent over time, which may not always be the case The recommendations given hence may not be applicable to the current business status 2 Literature review Brand name A study researched by Abdurrahman ISIK (2015) revealed that a brand establishes consumer awareness and desirability, facilitating consumer decision-making and driving brand purchases Consumers’ brand experiences shape their preferences for specific brands, either directly or indirectly The study’s results indicate that brand image has a positive and significant impact on consumer preferences The implication is that cosmetic users experience greater satisfaction with a brand when they perceive substantial experiential, social, and functional benefits from using it (Stephen L Sondoh Jr et al., 2007) Within Sephora’s products, brands ranking is determined by their target customer Previous research cues the relationship between brand perception and the preference of that brand, putting it in another way, increasing the favorability among customers H1: Brand names of Sephora products positively affect the number of people who rate them as their favorite Reviews Popular products are often deemed popular for specific reasons, and the presence of user reviews is a key factor contributing to this phenomenon Berger and Heath (2007) argue that individuals evaluate popular products based on the notion that others have found them worthwhile and have made the decision to purchase them The relationship between review count and product popularity is linked to the idea that a higher number of reviews signifies greater popularity At a behavioral level, individuals may infer that a product with numerous reviews has the highest value due to its widespread recognition and endorsement by other consumers In essence, the more reviews a product garners, the more it is perceived as popular and valuable, thereby influencing the number of people who mark it as a favorite Based on the established literature, we propose the following hypothesis: H2: The number of user reviews positively influences the number of people who have marked the product as a favorite Ratings Consumer ratings, typically presented as star ratings or numerical scores, play a pivotal role in shaping purchase decisions on e-commerce platforms (Chevalier & Mayzlin, 2006) High ratings are associated with product quality and satisfaction, often leading to increased sales and conversion rates (Mudambi & Schuff, 2010) Studies suggest that higher numbers of ratings contribute to greater perceived credibility (Park & Lee, 2009) Consumers may be more likely to trust products with a large number of reviews, believing that the aggregate opinion provides a Document continues below Discover more Introduction to from: Business… VJPE205 Trường Đại học… 7 documents Go to course Phân tích liệu 10 Vở ghi Phân tích dữ… Introduction to Business… None Final Report Guideline Introduction to Business… None VJPE205 HKI-23241 26 ftu Introduction to Business… None ECO231 Syllabus 9 Introduction to Business… None Bài viết Hướng dẫn cài đặt Azure Data… Introduction to Business… None De 212 - Bài tập vật more accurate representation of product quality Moreover, high-ratedlý products tend to receive in and engage with wellmore favorite marks, as consumers are more likely to show interest Introduction regarded items From the above information, it can be anticipated that the quantity and level ofNone to Business… rating positively affect the number of favorite marks H3: Quantity and level of ratings positively affect the number of individuals who mark a product as their favorite Price In research by Subaebasni (2019), the results of the data presentation between the price of customer satisfaction are a positive contribution and the results of the hypothesis indicate that the price variable has a positive and significant effect, so the price variable can be used as a benchmark against strengthening customer satisfaction Another research hypothesis states that price has a significant effect on consumer satisfaction Pricing is also very influential in attracting buying interest which also has an impact on continuous use (Yohanes Gunawan Wibowo et al., 2021) From previous studies, we expect that the price of each Sephora product has a significant impact on customer favorability H4: The price of Sephora’s products positively affects the number of people who rate it as their favorite Child count Child count in the Sephora data set indicates the number of variations of the product available The finding by Itamar Simonson et al (2006) that the variety a brand offers positively influences quality perceptions, even in a case where it makes the actual choice more difficult, underscores the effect of product variety on perceived brand quality Furthermore, increasing the variety of a brand offered enhanced quality evaluations of that brand even after participants were given the opportunity to actually experience quality Thus, the demotivating impact of large choice sets notwithstanding, it seems that offering increased variety can enhance brand perceptions In essence, we predict that the variations of a product will have an impact on the favorability of customers H5: The number of variations of the product available positively affects the number of people who rate it as their favorite Online only One of the most salient features of online shopping is its convenience and accessibility Research indicates that there are several factors that positively contribute to consumer satisfaction when shopping online, including convenience and accessibility (Li et al., 2020), personalized recommendations (Chen et al., 2020), and information availability (Verhagen & van Dolen, 2011) On the other hand, offline settings possess distinct characteristics that attract consumers First, offline shopping offers consumers a tangible and sensory experience that online shopping cannot replicate, which is a significant driver of satisfaction (Jones & Reynolds, 2006), especially in the case of beauty products such as perfume or lipsticks Interpersonal interactions in offline stores also contribute positively to consumer satisfaction (Arnold & Reynolds, 2003) Since each shopping environment provides distinct advantages, customers are predicted to prefer products available on both channels The label “only only”, which indicates products that are sold only online, is thus assumed to negatively correlate with the number of favorite marks H6: Sephora products “online only” label negatively affects the number of individuals who mark a product as their favorite Sephora exclusive The concept of “Sephora Exclusivity” integrates the notions of exclusivity and scarcity Exclusivity revolves around providing unique and limited products that make consumers feel special Simultaneously, scarcity emphasizes the limited availability of these exclusive items When consumers perceive these products as scarce, it intensifies their desire to own them, triggering a sense of urgency and increasing their value Research by Shi et al (2020) affirms that consumers with a strong inclination toward exclusivity tend to evaluate luxury experiences more favorably than those with weaker preferences Hamilton et al (2019) provided valuable insights, highlighting that scarcity cues effectively enhance consumers’ valuations of goods In the case of “Sephora exclusive” items, these cues strategically accentuate the limited availability of the products, thereby increasing their appeal and favorability among consumers Building upon previous studies, our hypothesis posits: H7: Sephora’s exclusivity positively affects the number of individuals who mark a product as their favorite New One prevalent perspective suggests that if a product brings a meaningful and distinctive novelty to the market, it is likely to contribute to its success When a product is perceived as “new”, it may spark interest and curiosity among shoppers, driving them to explore and eventually favor the product: “If newness provides meaningful differentiation to consumers in the marketplace, then it is related to market success” (Trijp and Kleef, 2008) This desire to experience something different and innovative can directly influence the number of individuals marking a product as a favorite within Sephora’s product range Based on previous studies, we can hypothesize: H8: The newness of a product positively affects the number of people who have marked the product as a favorite Out of stock The issue of products going “out of stock” is a common and concerning occurrence in the retail industry When a product is labeled as “out of stock” it signifies that the item is temporarily unavailable for purchase This situation can lead to customer dissatisfaction and, consequently, affect their shopping preferences and behavior Research conducted by Ranjan and Puri (2012) highlights that customers often feel dissatisfied when they cannot obtain the merchandise of their choice Moreover, Schary and Christopher (1979) conducted a study that delved into the consequences of products being out of stock They found that when items were not in stock, nearly 50% of consumers intended to take their business to another retail outlet, while approximately 20% decided not to make any purchase at all This indicates the potential loss of both sales and customer loyalty due to product unavailability Given the implications of “out of stock” situations on customer satisfaction, we can hypothesize: H9: Out of stock incidents negatively affect the number of people who mark a product as a favorite Limited edition Limited edition products are those produced in a restricted quantity for a defined period, creating a sense of rarity and exclusivity Product scarcity can influence how consumers evaluate and perceive the quality of a product In a scarcity-induced context, consumers may perceive scarce products as superior in quality compared to abundant alternatives (Raghubir & Corfman, 1999) Limited editions convey a sense of exclusivity, prompting consumers to perceive them as more desirable and prestigious (Van Herpen et al., 2005) This perception can lead to increased attention, motivation, and a willingness to pay premium prices for these unique items Moreover, the scarcity principle often works in conjunction with a sense of urgency Limited availability creates a sense of time pressure, encouraging consumers to make decisions quickly (Cialdini, 1993) This urgency can influence consumer behavior by increasing impulse buying and impulse decision-making, particularly in online shopping contexts (Wang et al., 2018) In Sephora context, these findings are expected to stay relevant, as illustrated by the positive relationship between the product’s status of being limited and customer love counts H10: Sephora products’ limited edition positively affects the number of individuals who mark a product as their favorite “new” (dichotomous): Indicates whether the product is new or not1 Chart 1: “new” distribution “online_only” (dichotomous): Indicates whether the product is only sold online or not Chart 2: “online_only” distribution “sephora_exclusive” (dichotomous): Indicates whether the product is exclusive to Sephora or not Chart 3: “sephora_exclusive” distribution Yellow represents (yes) and Blue represents (no) 12 “out_of_stock” (dichotomous): Indicates whether the product is currently out of stock or not Chart 4: “out_of_stock” distribution “limited_edition” (dichotomous): Indicates whether the product is a limited edition or not Chart 5: “limited_ edition” distribution 3.2.2 Descriptive Analysis This section will not include dichotomous variables, since descriptive analysis for these variables is unnecessary for they have only two possible values, making basic counts or proportions sufficient for summarizing their distribution Complex statistics like mean or variance are not applicable Hence, this descriptive analysis provides valuable insights into the distribution and characteristics of the variables: loves_count, rating, price_usd, brand_rank, reviews, and child_count, based on a dataset of 2804 observations 13 Table Descriptive Statistics loves_count rating price_usd brand_rank 0,512 reviews 2,331 child_count Mean 4,233 338,095 1,587 1,100 Standard Error 0,012 2,122 0,006 0,002 0,014 0,003 Median 4,239 340,737 1,544 0,477 2,420 1,041 Mode 4,460 256 1,505 0,477 0,602 Standard Deviation 0,627 112,349 0,301 0,089 0,753 0,151 Sample Variance 0,393 12622,303 0,090 0,008 0,567 0,023 Kurtosis -0,318 -0,089 0,749 0,492 -0,005 6,231 Skewness 0,046 -0,130 0,512 -0,184 -0,438 2,454 Range 3,436 617,283 2,151 0,398 4,328 0,944 Minimum 2,710 7,717 0,477 0,301 Maximum 6,146 625 2,628 0,699 4,328 1,944 948018,900 4449,100 1435,994 6537,025 3084,513 2804 2804 2804 2804 2804 11868,95 Sum Count 2804 Mean: The average loves_count is approximately 4.23, indicating moderate user engagement Ratings have an average of 338.10, and the average price_usd is 1.59, suggesting a moderate price range The brand_rank averages around 0.51, and reviews have an average of 2.33 Standard Deviation: Loves_count has a standard deviation of 0.63, indicating some variability in user engagement Ratings show significant variability with a standard deviation of 112.35 Price_usd has a standard deviation of 0.30, indicating moderate price variability Skewness: Skewness measures the asymmetry of the distribution After data transformation, all variables are close to zero, suggesting a relatively symmetrical distribution Overall, the data exhibits moderate variability, with some variables showing non-normal distributions and degrees of skewness 14 3.2.3 Correlation Analysis 3.2.3.1 Pearson’s correlation coefficient: continuous independence v dependence Figure Correlation Matrix Reviews and Loves Count (0.694): The number of product reviews significantly correlates with the number of people indicating a product’s popularity, with more people expressing their love for it Price and Loves Count (-0.223): There is a moderate negative correlation between the price of a product and its Loves Count This implies that higher-priced products tend to have fewer favorites, indicating that price may be a factor influencing customer preferences Rating and Loves Count (-0.131): The weak negative correlation between product rating and Loves Count suggests lower-rated products may attract more favorites, but other factors likely contribute to product popularity Child Count and Loves Count (0.341): Child Count, indicating the number of related products, has a moderate positive correlation with Loves Count, suggesting that more related items lead to more favorites, potentially due to a broader product range or customer loyalty 3.2.3.2 Point-biserial correlation: binary independence v continuous dependence Figure Point-bỉeial correlation The correlation analysis for binary variables reveals that online-only and new products exhibit negative correlations with Loves Count, suggesting fewer favorites for these categories Conversely, Sephora-exclusive products have a positive correlation with more favorites Limited-edition status shows a weak, statistically insignificant negative correlation The availability status (out of stock) has minimal impact 15 Hypothesis Testing 4.1 Hypothesis proposed Figure OLS Regression Results R-squared The R-squared value of 0.637 indicates that approximately 63.7% of the variance in "loves_count" is explained by the independent variables This suggests a reasonably good fit for the model The adjusted R-squared value, which accounts for the number of predictors, is 0.630 It is slightly lower than the R-squared, indicating that some variables might not be adding much explanatory power F-statistic and Log-Likelihood The F-statistic tests the overall significance of the model With a high F-statistic of 98.52 and a very low p-value (3.83e-111), the model is statistically significant The log-likelihood value is -228.60, representing the goodness of fit A lower log-likelihood suggests a better fit, and this value indicates a relatively good fit Coefficients 16