Identify the target group of consumers on
Daniel Cristian Fat
School of Computer Science
University of Lincoln
LN6 7TS Lincoln
Abstract — This report contain a set of data that will be analyses and used for further investigation in the consumer intention and behaviour. Therefore, there will be provided various information that will conclude into a research about online spending and Black Friday. Understanding consumer attitudes and motivation toward shopping both online and in-store. Retailers will have a better opportunity to market on Black Friday with an understanding of consumer intentions based on those findings.
This report introduces the understanding of consumers intentions on the Black Friday based on their age and gender. The experiments are conducted using the IBM Software, SPSS Statistics and the Black Friday dataset taken from Kaggle.
The dataset was specifically introduced on the Kaggle website for the purpose of identifying the customer purchase behaviours against different products, as being a regression problem where people tried to predict the amount of purchases in the discrepancy with the other variables.[Kaggle-https://www.kaggle.com/mehdidag/black-friday/home]
The online market keeps growing in the comparison with the previous years as the amount of time is spending at home has increased due to the embracing of a more flexible work timetable, with more people than ever able to work from home.
Nowadays, the society is dominated by the internet and mobile applications, where people are spending their time and money. Shopping by smartphone has also become much more popular, from 25% in 2016 to 36% in 2017, based on the age group under-35s of whom 63% bought Christmas presents via smartphone in 2017 in comparison to just 44% in 2016. (Mintel 2018)
One of most unpredictable group of people are teenagers because they tend to change their behaviour more often, since they are in a growing process. However everyone is aware of the Black Friday and the huge discounts.
Black Friday is an American holiday which is symbolised by massive discounts after the Thanksgiving Day. Nowadays this holiday has become popular in more countries since the vast majority of people are making their shopping online.
Since the large volume of sales for this specific day in the year, marketing analysts and data scientists have identified different patterns in customers behaviour, aiming to emphasise this knowledge in defining the most desired products.
In this research the dataset will be used for the purpose of identifying the consumer intentions, given the hypothesis that the women between the age of 18-25 years old are purchasing more products than the men from the same age group.
This hypothesis is created from the observation toward the female sex as being the one who is more aware of the seasonal offers in the clothes area. However the men are more oriented in the technological area of products, as an outcome they are spending higher amounts of money but not as often. Taking account of those two extremes, the hypothesis sustains that the women are spending more money as the result of their high frequency in shoppings.
What is the specific gender on which we should focus on ? How we can understand the consumer behaviour on a specified target group ? Which is the dominant gender in purchases ?
Esther and Ronald[ref] investigate in their research the consumer behaviour, motivation and intentions to aid for improvements of retailers marketing activities on Black Friday. The report established that consumers find online shopping more convenient than in-store shopping.
Furthermore, Black Friday is a very important part of the Christmas shopping period with 51% of Black Friday clients. Saying that the majority of their purchase. During the event where Christmas gifts while 74% of clients said that at least some of their purchases were Christmas gifts. Also, Mintel's report estimates that Black Friday spending rose to £4.2 billion in 2017, up 13%
Mintel's research found that online had become almost as commonly used as 68% of UK consumers bought items online. Nevertheless, the age group between 16 and 24 grower to 83%. However, younger consumers are more probable to shop around than older consumers when spending both in-store and online. (Mintel 2018)
Figure 1: Change in online shopping use, by age and gender, April 2018
Retailers as Amazon, which is one of the most dynamic and innovative retailers in the UK at the moment is overtaking the monopoly of the market upstaging even other big retailers as eBay, which is one of the fastest-growing online operators in the UK. The retailer uses its data-driven insights to calculate and implement pricing strategies that create matchless, lowest, price perception. (LinkedIn 2017)
Esther and Ronald[ref] identified the divergence between the male and female as an effect of their differences in terms of shopping on Black Friday. In this perspective men are more likely to look for technological products. On the other side, women are attracted to festive shopping caused by their enjoyment for this holidays, therefore the experience has more meaning.
However, because of the discrepancy between gender, retailers as Amazon and eBay are scaling their sales more than other retailers using strategies of keeping the customers in their field of action, but also providing a diversity of products from all categories. [Online Retailing -UK -July 2018 - Executive Summary]
Figure 2: Retailers shopped with in the past 12 months, April 2018
Data were obtained from Kaggle which is an online community focused in the area of data science and machine learning. In order to conduct our research, the dataset needs to be cleaned for possible missing values, this process is realised with the help of SPSS Software which will parse the data and eliminate the rows where the data is missing. Thus the data can be used and the project can move into the next stage.
At the next point we can read and understand the data and apply descriptive statistics methods to our dataset.
Figure 3: Descriptive statistics generated in IBM SPSS Statistics
In the next section we need to identify the population in concordance with the hypothesis. For this precise task we are going to give a more visual understanding to our data.
Figure 4: Bar chart for the mean of Purchases filtered by Ages and Genders
Right now we have a better understanding of our dataset and we can start applying correlations to determinate the relationships between those variables and to identify which quantitative method would be better to use.
Following the hypothesis, we have to filter the dataset to let us to work with the targeted group. Also the columns which are not used in this research will be erased from our dataset, followed by applying descriptive statistics on our filtered data. Figure 3: Descriptive statistics generated in IBM SPSS Statistics for the filtered dataset
At this point we can use Spearman Correlations to identify the rank
This text is for keeping the font style.
Conclusion - 1/2pg
This text is for keeping the font style.
Tripathi, A. (2017) Decoded: Amazon's Unique Competitive Pricing Strategy. 13 September. [online] available from <https://www.linkedin.com/pulse/decoded-amazons-unique-competitive-pricing-strategy-amitabha-tripathi>
Mintel (2018) Online Retailing - UK - July 2018 [online] available from <http://academic.mintel.com/display/926106/?highlight>
Mintel (2018) Christmas Shopping Habits - UK - February 2018 [online] available from <http://academic.mintel.com/display/858849/>
...(download the rest of the essay above)