VVM’s Shree Damodar College of Commerce & Economics, Margao-Goa in association with the Directorate of Higher Education (DHE) Government of Goa, organized a One-Week National Level Workshop on “Implementation of Data Analytics in the BFSI Sector” from 13th December to 18th December 2021 from 9.30 am to 4.00 pm in the Smart Classroom. Data analytics is indeed a revolution in the field of Information Technology. The workshop was intended to disseminate knowledge relating to implementation of Data analytics in various sectors. i.e Banking, Financial Services and Insurance. This workshop is a step in the direction of enhancing the skills of students, research scholars and the teaching community.
The objective of the conference were devised as:
To help the academic community understand emerging trends in the BFSI sector.
To expose the participants to real life cases in these areas.
To provide hands-on experience in using data analysis tools and techniques
To enhance the analytical and application skills of faculty members, students and research scholars from the disciplines of Commerce, Management, Engineering, Computer Applications & Economics.
To enable faculty members to design add-on skill development courses or modules to fill the skill gap.
There were a total of 36 participants out of which 8 were teachers and 24 were students. There were 4 technical sessions each day which dealt with different aspects of Data Analytics and its implementation.
Day 1: Monday, 13th December 2021
The Workshop began with an Inaugural Function. Principal, Dr. Prita Mallya welcomed all the guests, participants, faculty members and students to the One-Week National Level Workshop and assured them of a rich learning experience provided in this workshop through a blend of both theory and practical sessions. The workshop coordinator, Ms. Sharmila Kunde, addressed the gathering and explained the relevance of this workshop in real world and its applicability in different areas. She made the participants aware about the theme of the workshop, and the rationale behind it in social context. She briefed the participants on the importance of attending such workshops, the need of data analytics in the field of research and gave an overview about the conference. Ms. Ashwini Devari and Ms. Lizia Gomes, Asst. Prof in Commerce introduced the Resource Persons, Dr. Hemant Palivela,a Senior Research Scientist & R&D manager at Accenture Solutions Pvt. Ltd. and Mr. Sarveshmani Tiwari, a Data Scientist at Eclerx Services, Mumbai. A memento was presented to them as a token of gratitude and appreciation. The inaugural programme concluded with a Vote of Thanks proposed by the Vice Principal, Dr. Rodney D’Silva.
On the 1st day, during session I, Mr. Sarveshmani Tiwari covered the following concepts – random variables, continuous and discrete variables, sample space, events and random experiment, an overview of the different concepts of probability distribution, hypothesis testing. In session II, he provided the conceptual knowledge about testing hypothesis and parametric testing, Type I and Type II error in brief. The importance of probability in data analytics and various forms of probability theory and its association with data analytics were also covered. Dr. Palivela commenced the third session by explaining the concept of Binomial Distribution, Binomial Theorem, Poisson distribution, Normal distribution theory, bell curve and the applications of normal distribution stating various examples. He discussed the concept of Exponential Distribution and its applications in detail. In order to facilitate better understanding, he used several case studies to support his explanation.
Dr. Palivela elucidated on the potential application of data analytics in Banking, Financial Services and Insurance sector and familiarized participants with various concepts of probability and related topics that a data analyst ought to know during the fourth session.
Day 2: Tuesday, 14th December 2021
On the second day of the workshop Dr. Palivela covered the following topics: Confidence Interval, Inter Quartile range, Central Limit Theorem, Mean, Mode and their applications with real life examples, Hypothesis Testing- concept, error involved in hypothesis testing and steps involved in hypothesis testing using practical examples. He stressed on various statistical techniques and tools such as Z-Score, T-test, ANOVA – Concept, steps and applications and its importance in the field of research. He was able to convey to the participants the different methods/ tools and tests that can be used in conducting systematic research.
Mr. Sarvesh engaged the next session and demonstrated the following topics using Jupyter Python notebook. He explained the fundamentals of Descriptive Statistics, Conditional statements, generating sequence numbers, control flow statements and IPL Dataset Descriptive Analysis (Summary of Data – Slicing and Indexing of Data frame – Value count and cross tabulation – Grouping and Aggregation – Applying operations to multiple columns) with an example on IPL Dataset Descriptive Analysis and Handling Missing Values.
Day 3: Wednesday 15th December 2021
On Day 3, Mr. Sarvesh Tiwari, explained the topics in Data Exploration and Visualization. Various sub concepts such as Bar plot, box plot, scatter plot, hectograph, scatter plot and so on was also discussed. Later, he emphasized on Regression Analysis: Linear regression with practical example. The Resource Person continued the explanation of the fundamentals of Regression Analysis in the second session. He also explained the assumptions for Linear Regression Analysis with examples.
The third session was handled by Dr. Palivela who explained the concept of Multiple Linear Regression stating an example of how to price the tickets when you have a waiting list in Indian railways. Further he exposed the participants to Linear and nonlinear equations, discussed the assumptions for Multiple Linear Regression, Random Correlation and Residual value in his fourth technical session.
Day 4: Thursday 16th December 2021
On Day 4, first session was engaged by Dr. Palivela, who covered the topics on Decision science that is the Data Science which is categorized into Unsupervised and Supervised techniques. He explained the concepts in detail by further categorizing the supervised techniques into Classification and Regression techniques with examples. This was followed by Unsupervised techniques that consists of clustering which includes DB Scan, K-Means and Agglomeration, Logistic regression, Decision trees and K-mean techniques, the types of Logistic regression that is the Binary, Multinomial and Ordinal type was explained with examples.
Mr. Sarvesh Tiwari engaged the next session during which he explained the Logistic Regression techniques with examples of the credit status in Banking sector data set and the accuracy of the model was analyzed. Another example on Weather and Rain Prediction was discussed for understanding the two categories of Categorical Encoding namely the Label Encoding and the One Hot encoding.
During the next session, Dr. Palivela explained the topics – Recursive Binary Splitting, Decision Tree and Entropy and Support Vector Machines with real world examples. He further discussed on the Uncontrollable and Controllable variables and their analysis.
Day 5: Friday 17th December 2021
On Day 5, first session was engaged by Mr. Tiwari. He started with the explanation of the Usecase on the Detection of Fraudulent Credit Card Transactions for customer benefit. The detailed step by step analysis of the usecase was covered. He explained the Random Forest classifier and applied the same concept for the considered usecase. The second session started with hands on running of the code in Google Colab on the credit card data. The session was then continued with analysis of the results of different classification algorithms namely Decision tree, Random Forest, K-nearest neighbor and Logistic Regression to study the performance of the model. The SMOTE algorithm was explained for oversampling and under sampling with code.
The Resource Person for the third session was Dr. Palivela. He explained the usecase on Market Basket Analysis in detail, with step by step calculations done by the participants. Further, Apriori algorithm was discussed, applied to a data set and results generated. During the fourth session he explained Cloud Computing and Python as a language, stressed on its benefits with the working mechanism of the cloud. The methods like Wordcloud, TreeMap and steps of Apriori were shown.
Day 6: Saturday 18th December 2021
On day 6, the 1st session was engaged by Mr. Tiwari who explained the Customer Segmentation usecase in detail with the code, did the execution and briefed on the analysis of it. Further, Clustering technique was applied and the output was analysed. The considered usecase is for identifying the target customers for a shopping mall whose detail analysis can be given to the marketing team for deciding on marketing strategy. All the participants were provided with Kaggle customer segmentation reference to work with and to run the code for applying K-Means Analysis and to generate scatterplot, swarm plots and box plots for detailed anaytics. Finally, a 3D model for analytics was depicted and code was executed to understand the in-depth analytics with a 3D view. Next, he gave a brief introduction about Data Visualisation and its impact with example of Google Analytics and Covid Realtime Dashboard so that the participants understand the power of Data Visualisation. Towards the end of this session, he gave a brief introduction of CLTV, that is, Customer Life Time Value which was explained in the subsequent session.
Dr. Palivela engaged the next session by briefing on the steps of solving a Data Science problem and reviewed all topics covered during the workshop. He focused on his profile and experience and inspired the students and the participants on the key areas to focus onto become a data science professional. He said that knowing programming is a must for any domain and for students from every background. He also said that Data Science Basics, understanding the objective of solving a Usecase and the way of delivering the output to the client or stakeholder is of utmost importance in this field. Dr. Hemant mentioned numerous experiences which focused on how an individual should build up a presence online, through his or her work specialization. Towards the end of the session, the Participants asked queries which were resolved by the Resource Persons.
The Valedictory Function was held after the lunch break. Ms. Abigale Rodrigues presented a report of the one-week workshop briefing on all the topics covered by both the speakers during the week. A few participants shared their experience and the feedback of the entire workshop. Later on Mr. Tiwari and Dr. Palivela awarded certificates to the participants and also gave their feedback about the entire workshop. The program concluded with a Vote of Thanks proposed by Associate Professor, Dr. Edwin Barreto.
The one week workshop was a great learning experience to all the participants.