our clients journal entries for fraud risk. To assist with the fraud testing, you have transformed your clients journal entry data into the following visualization. In this visualization, journal entries are grouped based on similarities that the machine learning algorithm identified. In this case, the similarities are the journal entry size (horizontal axis) and journal entry time of day (vertical axis). Using this visualization, answer the following questions.

A scatterplot compares the time of day the journal entry was posted to the journal entry amount. The vertical axis ranges from 12:00 a m to 10:00 p m, in increments of 2 hours. The horizontal axis labeled, Journal Entry Amount, ranges from 0 to $800, in increments of 100. Three sets of scatterplots are plotted on the graph. Major portion of the first scatterplot ranges between ($90, 8:00 a m) and ($210, 8:00 a m). Major portion of the second scatterplot ranges between ($290, 8:55 a m) and ($700, 4:00 p m). Two data points of the third scatterplot ranges between ($550, 3:55 a m) and ($600, 4:00 a m).

What type of data analytics technique did you use? Does the technique use supervised or unsupervised machine learning? Did this data analytics technique detect any anomalies? If so, explain. If there are anomalies, do they indicate a risk of fraud? If so, explain.