Assignment 06: Hack your tracker / Untrack me
ABOUT: Develop a method to hack one (or more) of your tracking apps. Software or hardware solutions or a combo of both are welcome. Document your process. Write a short reflection about your hack - how did you do it? What information is gained or lost? What are the implications of hacking your data in the way that you did?
This part is not closely related to this week's homework. I did this research because after I saw the UNFIT BITS project, I was so curious about how can my friends on WeChat have more than twenty thousand steps per day. So I did some research on how people can hack WeRun and make benefits.
You can track your daily step count and see how close you are to reaching your fitness goals. If friendly competition helps motivate you, you can see how you stack up with friends who also follow the Official Account on your personalized leaderboard. As an added incentive, if you finish first on the leaderboard by the end of the day, you’ll be able to set the cover photo on all your friends’ leaderboards!
What can people do with WeRun besides keeping fit?
Employee: "I will go to visit a customer."
Four hours later, the employer checks the WeRun ranking.
The employer: "Why did he (the employee) only take 2000 steps today? Did he really go to visit a customer?"
A couple is chatting on their phones.
Man: "I will go to sleep. Goodnight, babe."
Half an hour later, the woman checks the WeRun ranking.
Woman: "Why did he take 2000 more steps after he said he went to sleep? Where did he go?"
You can make money with the background image.
The place of the background image can be used to advertise. So some companies hire the top ranking people to publicize their companies or products.
How do people hack WeRun?
A Swinger Stepper.
You can buy it online with a few bucks.
The Tracker I Want to Hack
The Recommender System of Taobao
Recommender systems have become increasingly popular in recent years. For example, Amazon is well-known for personalization and recommendations, which help customers discover items they might otherwise not have found.
"Recommender systems typically produce a list of recommendations in one of two ways – through collaborative filtering or through content-based filtering.
Collaborative filtering approaches build a model from a user's past behaviour as well as similar decisions made by other users. Content-based filtering approaches utilize a series of discrete characteristics of an item in order to recommend additional items with similar properties."
Taobao, one of the most popular Chinese online shopping websites, is also well-known for its recommender system. How does its recommender system work has long been a secret. From many users feedback and my personal experience, it seems that the recommender system of Taobao uses methods besides the two types of filtering approaches listed above.
Based on many people's investigation and analysis, it seems that Taobao's recommender system does such things as following.
1. Getting data from user's input methods.
If users use a third-party input method, Taobao can calculate what they want to buy based on the words they entered in chatting.
2. Getting data from user's microphone. This kind of situation does not happen very often, but some users say that Taobao will recommend products which they have talked about with others.
Although these two conjectures have not been officially confirmed, they are not completely impossible by observing the differences between the settings of Amazon App and Taobao App. Why do you think Taobao wants to access so many parts of our phones (microphone, camera)?
The Way To Hack
Step 1: Creating different accounts to buy different things.
Step 2: When talking about your shopping list with others, use emoji!
In this way, Taobao has to transfer the emojis to words before they get the accurate data.