MARKETNG2505 | Market Research | Practical Uses of Market Baskets

Describe:

• What the data is like (with some examples)? Consider providing some hypothetical examples.
• What type of benefit do you hope to get from market basket analysis?  What major questions are you attempting to answer?
• Is there anything being done in market basket analysis involving time?  For example, it is one thing to know a person might choose "option C" next ... but how long might it take?  (Feel free to do some external research on this.)
• In your opinion, how does market basket analysis differ from clustering?  Is market basket analysis a special case of clustering?  Or are they completely different?  Explain your answer.

?Be sure to address each point in your main post.  Also, be sure to illustrate with an example (e.g., if you think market basket analysis is relevant, describe what you think a likely cluster might contain and what the real-world meaning would be).

Answer:

What the data is like.

The data of market basket analysis is quite common as well as useful for both the customers and the business organizations (Olson, 2017).The chief aim of market basket analysis actually is to understand what the products are which the customers purposefully purchase together.For example when a customer by is chicken then he also buy is the spices vegetables and other materials for cooking that chicken or when a customer buys a mobile phone then he or she also buy the accessories needed for operating the phone like ear phones or phone cases.

What type of benefit do you hope to get from market basket analysis?  What major questions are you attempting to answer?

Market Basket Analysis is the most common and essential types of the data analysis that has been recently seen to widespread for the interpretation of the purchasing patterns of the consumer. This analysis is commonly used for the retailing and marketing purpose. This helps the business persons to know the customers choices about one particular object. Once it is known that the customers who will buy one product prefer or feeling necessity to buy other related things, it is possible for different companies to attach themselves and market those products together. This method will help them to make the customers of the product, targeted prospects for another. This will help the shop managers to get the knowledge about the products preferred by the customers so that they can stock huge amount of similar products along with the main one (Kaur & Kang, 2016). They also can place those items optimally in their store so that it becomes easy for the customers to pick similar things together (Shiokawa et al., 2017). This will enhance the selling of different types of products together and bring profit for the stores as well as those companies. One of the most common examples of the market basket analysis is that the supermarket store performing an analysis and study found out that the grocery items, together with the baby products and beers sell well on Saturdays. The example illustrates the fact that the couples tend to stock up their kitchen on supplies for themselves and their family before the starting of the week (Gupta & Mamtora, 2014). The strength of this analysis lies on the fact that by the effective usage of the data mining tools of the computer, it is not required for an individual to assume the products the consumers will want to buy, but the sales data of the consumer will speak for itself.

Is there anything being done in market basket analysis involving time?

The promise of market basket analysis is to understand the algorithms so that the companies can crunch data and find the most interesting patterns and exploiting the business. Market basket analysis has closed connection with time for example the business organizations can understand the demand of the market and what patterns are effective for reaching the customers. In case of the online marketers it becomes easy for identifying the exact requirements of the customers in no time. In online marketing the customers are provided with huge number of choices from which they can choose one and get immediate choice for all the accessories needed for using the first product. In that case the buying option becomes quite easy and less time consuming. The marketers get immediate response to those products hence can stock them in no time. In case of offline purchasing the markers do not get immediate reactions of the customers about their purchasing or identify their purchasing patter that is why they wait for more time. Some of the commonly used metrics for the market basket analysis is support, confidence and lift. Support means the percentage of the transactions that includes item set and are preferred for being preferable in future transactions (Nengsih, 2015). Confidence illustrates the probability the transactions contains items on the left hand side of the rule. Lift explains the probability of all the possible items of the rule divided by the probabilities of the items of the left and the right hand side. The performance of the market based analysis and the identification of the potential rules requires data mining algorithm commonly known as the Apriori algorithm

 How does market basket analysis differ from clustering?

Clustering is the method of accumulating a group of objects in a way that this group of objects can be similar to the objects belonging in other different groups (Videla-Cavieres & Rios, 2014). On the other hand, market basket analyses the objects are not grouped like clustering rather have individuality in their applications.Therefore it can be said that the market basket analysis is a special kind of clustering where the sellers offer different types of things differently from which the customers choose one or similar objects according to their utility. From the explanation of the set theory, considering the sets (A, B) and (B,C) to be frequent whereas the (A,C) is not, it is important to check the rule for (A,B,C) for narrowing down the possible association of the rues of market basket analysis

References:

Gupta, S., & Mamtora, R. (2014). A Survey on Association Rule Mining in Market Basket Analysis. International Journal of Information and Computation Technology. ISSN, 0974-2239.

Kaur, M., & Kang, S. (2016). Market Basket Analysis: Identify the changing trends of market data using association rule mining. Procedia computer science, 85, 78-85.

Nengsih, W. (2015, May). A comparative study on market basket analysis and apriori association technique. In Information and Communication Technology (ICoICT), 2015 3rd International Conference on (pp. 461-464). IEEE.

Olson, D. L. (2017). Market Basket Analysis. In Descriptive Data Mining (pp. 29-41). Springer, Singapore.

Shiokawa, Y., Misawa, T., Date, Y., & Kikuchi, J. (2016). Application of market basket analysis for the visualization of transaction data based on human lifestyle and spectroscopic measurements. Analytical chemistry, 88(5), 2714-2719.

Videla-Cavieres, I. F., & Rios, S. A. (2014). Extending market basket analysis with graph mining techniques: A real case. Expert Systems with Applications, 41(4), 1928-1936.