1.Leveraging data science to identify most efficient bank branches
Problem statement: The problem statement is to find the efficiency of bank branches using the net average surplus of all branches and find the in-out transaction of specific branch.
Solution: First We analyse the data of which contains details of all the branch’s transaction. And find the In -out transaction per day and also find the total surplus per day. For this first of all, we group the data based on the branch so we can do operation specific to branch we split the data into two dataframe checkin and checkout. Applying data reprocessing, then sum of the amount with same date so we can have the total checkin_amount and checkout_amout per day. And merge these two dataframe and add new column named net_amount which indicate the total surplus per day. And finally plot this. (See the screenshot )
Then second one is finding which branch is more efficient branch for this we use the newly created grouping dataframe which have columns like branch, checkin_amount, checkout_amount, net_amount. so we first do sum of the net_amount of specific branch and create new dataframe with the column branch, net_average. And Plot the bar chart which defines the top to bottom branches.
2.Drag and drop data analytics using knime (pricing prediction)
Problem statement: In data analytics feild, the main point is about to use the algorithms which are used for predicting the result based on the analysis. But the current situation is about if you wanna be a Data Analyst, you have to know any of the Programming Language. But if any non-technical person want to do some work in data analytics then he/she want to learn the programming language first then he/she can do some stuff in Data Analytics. So the problem statement is about to do Data analytics with drag and drop.
Solution: For drag and drop type data anaytics, some the software is Knime, Alteryx etc. It gives all functionality that the programming language gives. For this we have used Knime for predicting the price of the area based on the data which is in form of CSV file. First we have read file using File reader node after that applying scatter plot which plot a graph and then applying linear regression algorithm so that we can predict the price of area.