| 1 | the step by step homeworks that allowed me to familiarize myself with the different softwares, specifically Tableau and R |
| 2 | This is the only course I have ever taken at Purdue that I learned practical information that I will take with me to my job. Everything we learned is important and useful.The professor has a very relaxed buy engaging teaching style. |
| 3 | The instructor teach us how to use the software to solve the problem |
| 4 | Take Home Exams, grading attendance |
| 5 | Professor Lanham has provided me with the skills to become a successful analyst no matter what career track I take. By teaching and applying various methods, tools and softwares that are commonly used in the field of data analysis am confident that this class has set me up well for a career in analytics. |
| 6 | Great material, great professor, just great overall. |
| 7 | Every piece of material was tied back to the big picture and real world applications. |
| 8 | Data Clean up and Data Visualization |
| 9 | Assignments are excellent. Help me reviewed the things I've learned step by step which is extremely helpful. |
| 10 | Almost everything! |
| 1 | not explain the code very well, sometime, instructor just give us the code, but I want to understand what the code is and how to use it |
| 2 | We had several cancelled classes due to the professor having a lot on his plate. |
| 3 | Really not much to say on this aspect-other than Professor Lanham occasionally cancelling class due to his various committments outside of this class and Purdue, there really isn't much to complain about. |
| 4 | None. |
| 5 | It felt like things covered in class didn't always follow the homework, and the take home exam would be much harder. I felt intimidated because it seemed that everyone understood everything but I was new to everything. Maybe more step by step tutorials would be helpful, it was helpful having notes on BlackBoard. I really did not like the classroom setting as it was difficult for me to pay attention given how far away the screen was. |
| 6 | I would say it has gone a little bit too far. Especially for students do not have any foundation in data mining (like me). |
| 7 | I wish I could have done more in-class exercises and assignments. |
| 1 | spend more time about the code |
| 2 | The professor did not need the entire class period more often than not. MWF classes might make a very important class like this more accessible. Additionally, I was lucky to have heard about this course by overhearing two students talking. I think this class would be extremely beneficial to many students from the College of Science and beyond. More awareness of this course is necessary. |
| 3 | Possibly less group homeworks and more individual assignments. Though I understand why it was set-up like this-having an individual assignment would allow for increased participation and understanding of the material. |
| 4 | Possibly do a group case that has you answer some form of real world analytics problem so it ties learning to real world problems in a way that more students will be able to see the connection |
| 5 | None. |
| 6 | Know that there are absolute beginner students in the class as well. |
| 7 | Having more in-class exercises and assignments. Also, when it comes to teaching the concepts, I would suggest painting the big picture first and then explaining how all the parts taught throughout the semester fit in the big picture. As of now (at the end of the semester), I have knowledge of different concepts of struggle to understand in what scenarios they are applied or how all of them tie together (which I think is a bit unfortunate since the course and professor are so promising). |
| 8 | Change the grader - change to anyone who has a better handwriting. |
| 9 | Add a Web Data Scraping component to get data from various places from the internet and combine them using the tools provided instead of simply providing us with the datasets. |
| 1 | explain the idea of course |
| 2 | This professor is awesome. He is very helpful and class material were supported me to do real stuff and learn something. |
| 3 | The instructor is really passionate about the course content which encourages students to be more involved and work in the course. |
| 4 | Teach real world examples. Every single class Professor Lanham would relate what we are learning back to his work in the industry and how he used these techniques. It is refreshing to learn something that is not theoretical or outdated, but it being used every day. Also, I know this is a course for Krannert students and therefore the target demographic doesn't really care about what is going on under the hood of these algorithms and processes, however, I really enjoyed learning about them. I think that he should continue to teach this. |
| 5 | Relates the material back to work applications. Takes our feedback into consideration and puts a great deal of work into making the homework comprehensive and relevant. |
| 6 | Professor Matthew is a very unique professor. As we, as students would say, he "cuts the crap" and really crafts a semester curriculum focused on preparing students with applicable, useful information. He raises the bar for us and tells us what we need to know (and not know) to be successful. I wish more professors would adopt a teaching mentality similar to Professor Matthew. |
| 7 | Professor Lanham shows continued passion in absolutely vital field of Data Analytics, and spreads that passion onto his students. Through guess lecutreres, demonstrations and applied homework exercises, even an average/lazy student will walk away with something beneficial from this class. If I am to succeed as an analyst-a lot of it will be due to Professor Lanham. Because of him-I am planning on pursuing my Masters in Analytics. |
| 8 | Matt does a great job of showing real world implications of the skills we are learning in class. He keeps the class fun and enjoyable to be in while you gain exposure to different softwares that are common in industry to help us realize how they can affect our daily work life. Matt also makes sure to have interesting guest speakers to even further show how some of these tools are being used in industry to expose us to what we could be looking to do in the future. |
| 1 | try to spend more time on the code so that when the question change, we know what to do, and since the class is 75 mins, we can spend 15 mins on the practice or quiz that related to that class so that not only help us to understand the course material but also help us understand the code.
The quiz or practice could count as an attendance or could be part of the HW which may is difficult. |
| 2 | I would suggest organizing your lecture slides better on blackboard! I understand they are organized by concept but maybe include a key to help locate which ones were presented on which days? Finding the relevant presentation was impossible sometimes. Moreover, I love the topics and concepts you are teaching. I would suggest not giving that up. However, since the bar for learning is raised, consider including more exercising in class that students can do with you (and turn in as participation for credit) every day with you. That way we can ask questions in class, really understand what you are teaching that day, and decrease the learning curve when exam and homeworks are due. |
| 3 | Certain topics seemed disorganized/dry that the student lost interest quickly. The transition from Data Mining to Predictive modeling was definitely one of those phases when a lot of students felt lost. I think introducing predictive modeling techniques with more intuitive models(like Market Basket Analysis) before jumping into the complex models(Kohonen Clustering) will help students form a better impression.
Further, I think taking a handful number of datasets and using them across the semester will help students feel more connected to the class and arriving at the solution towards end of the semester for a business problem that was worked upon for a while will bring closure to the concepts.i.e., Use a HR(or retail) dataset and follow the data cleanup/data visualization, predictive modeling etc., on the data set and evaluate the final solution after several models were used on the same dataset. |
| 4 | Break the lectures with small review questions to keep reinforce learning. |
| 5 | Being more accountable for classes. I understand that Professor Lanham is very busy, however, this is the only class I truly enjoyed going to this semester and I wish we would have been able to cover all the topics originally planned. |