https://padlet.com/tchr68019/46bzz5teghdmo6z0 Write in your own words how machine learning is used in following applications en-us 2021-09-03 05:33:03 UTC 2025-10-21 00:44:47 UTC hello@padlet.com https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714745815 It uses machine learning by comparing the email with pre-stored models of safe or SPAM emails. As it runs through, it detects whether it is closer to a safe email or a SPAM email]]> 2021-09-03 06:26:27 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714745815 umar6693 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714748160 This is done using collaboration filtering in which if two customers have the same shopping behaviours, they are shown a similar type of shopping list to fit their interests or needs which the machine learns with its past experiences of other customers.]]> 2021-09-03 06:28:03 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714748160 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714750311 Machine learning in spam works by collecting data in the email such as its contents, sender name and headers. It removes stop words (those that connect sentences) and punctuation but keep the keywords which leaves only relevant data. Then this data is scanned and certain words/phrases commonly used in spam such as lottery, earn and other words help indicate the incoming email is likely spam.

This learning model is build and tested to ensure it learns what emails are spam by previous experiences and then the model is finally published live.

]]> 2021-09-03 06:29:51 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714750311 wali0047 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714750444 it uses machine learning through carrying out a cleaning process in emails that cancels or erases elements that dont carry relevent info like " and,like,with and punctuations".
than scans through the rest of the data to see if words like "lottery,win,full,prize etc" are used ,if this requirement is fulfilled it is likely that the said email is SPAM]]> 2021-09-03 06:29:59 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714750444 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714754012 uses machine learning comparing email with pre stored models and spam emails. when it runs it sees whether it is a spam email or safe email.]]> 2021-09-03 06:33:05 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714754012 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714754138 Machine learning in recognizing user buyer history works via collaboration filtering, which is the process of predicting a new customer's buying habit by comparing it with other buyers. As such, if person A buys a book and a workbook, 2 weeks later Person B may also buy the same book, and the machine will suggest the workbook due to its past experiences and linking.
This is particularly common in creating music playlists.]]> 2021-09-03 06:33:11 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714754138 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714755762 Machine learning collects the data in an email and it detects words which are often used in spam emails, once it has catogerized an email as spam it will filter it out ny deleting it]]> 2021-09-03 06:34:33 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714755762 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714756615 Machine learning is able to filter through your recent buying history, seeing which category each items fits in. It is then able to link all your recently purchased items, then it will recommend to you something which also falls in that category. Or some browsers are also able to tell what others users next bought who originally bought this]]> 2021-09-03 06:35:14 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714756615 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714759437 done using collaboration filtering in which two customers have same shopping behaviours , they rae shown a similar type of shopping thier interest or needs]]> 2021-09-03 06:37:11 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714759437 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714766440 Machine learning is able to detect fraudulent activity by comparing the new action with the base examples stored in it already. First it collects the data. Then it will separately analyze all components of the data, comparing it with its training for tracing fraudulent data, that teaches it how to recognize faulty stuff]]> 2021-09-03 06:42:00 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714766440 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714767829 Machine learning in detection of fraudulent activity works by gathering data from surveys or the internet. These are used to detect multiple factors such as cred card fraud, information on customers and shopping habits. Redundant data is removed so that only key words remain, this has to be done carefully.
Then the algorithm is trained to detect fraud. The model is tested with known data and known outcomes and is modified if it does not satisfy requirements.]]> 2021-09-03 06:43:07 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714767829 faizan3536 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714768169 2021-09-03 06:43:24 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714768169 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714770144 The machine learning in this application stores data from previous spam emails by taking the keywords like lottery as data and when some spam email is approached they compare the keywords if many of them are matched it gets to know it is a spam email.]]> 2021-09-03 06:44:52 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714770144 faizan3536 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714772674 2021-09-03 06:46:51 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714772674 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714774366 It is completed using collaboration filtering which is a process in which machine learning is used to determine what a customer might like based on a previous customers opinion.
If one person buys a specific cd and some health care products and the next person buys the same cd. The machine learning process will recommend buying the same health products as the first person.]]> 2021-09-03 06:48:18 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714774366 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714775744 This happens when the machine learning stores data of two similar customers who have similar shopping behaviours. The data is compared and suggestions are given to the customers.]]> 2021-09-03 06:49:23 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714775744 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714779668 it is able to detect fraudluent activity by activity by comparing the new action with base examples stored. it will then separately analyze all components of the data, comparing with training for tracing fraudulent data , that teaches hoe to find faulty things]]> 2021-09-03 06:52:31 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714779668 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714780332 Data is gathered from surveys, the web and real life examples of fraudulent activity. It is given to a machine along with data on how things could be fraudulent for example; a person spends a large sum on jewlery. The model is tested and is modified if some acts of fraud are not detectable.]]> 2021-09-03 06:53:05 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714780332 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714781344 In a fraudlet activity the machine learning check the previous data of billing that tells it the things that the owner buys from the card. It then compares any unsusual activity with the previous data like if a person does not like something but a transaction is done on that it is not usuall and the machine learning due to this activity gets to know this is a fraud.]]> 2021-09-03 06:53:57 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714781344 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714787870 Machine learning is used in this application by comparing emails with pre stored models and spam emails. When it runs through, it sees whether it is closer to a spam email or safe email. ]]> 2021-09-03 06:59:34 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714787870 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714839783 First an algorithm is used to collect data then the machine carries out a cleaning process in which it focuses on keywords like “lottery”, “full refund” etc. these words are mostly used in spam emails, indicating that this email is likely a spam email and the email is then added to the spam folder and is tested live.]]> 2021-09-03 07:43:19 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714839783 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714844637 This comes from collaboration filtering which is, that customers with similar shopping behaviour are compared ex. if customer A buys a jazz cd and a roman history book and customer B buys a jazz cd the machine will recommend customer B to buy a roman history book since the taste of both the customers in shopping is similar.]]> 2021-09-03 07:48:06 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714844637 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714851346 data is gathered by web scraping ex, info about customer ,and to detect credit card fraud.Then the redundant data is removed carefully.
Then a model is built based up on learning from the data and it can now be used to detect fraud.]]> 2021-09-03 07:54:09 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714851346 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714969957 First of all, when an Email is checked via machine learning it scans for connecting words like or, and, but, etc. Then it deletes these words and makes it a simple paragraph. Then the Email is again checked for words like lottery, win, prize , full, etc. If these words are found then it is considered to be a SPAM Email and then machine learning informs the user about it after that if any kind of action which machine learning doesn't know takes place the machine learning takes notice adopts that method or action.]]> 2021-09-03 09:52:34 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714969957 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714984722 A machine is trained using a training data base. This database trains it according to incidents regarding spam emails. When a receiver receives an email, the machine first figures out the structure and presentation of the email. Next, it reduces the content in the email by eliminating the stop words and punctuations. Finally, it searches for commonly used words in spam emails e.g. lottery, won, earn, money and more.]]> 2021-09-03 10:10:19 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714984722 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714988747 In this application machine learning gathers data from the database that what the user buys and how many times he or she buys off the online stores for example if a user buys a shirt of his size and style of an online store more than once or twice then the machine learning checks the database and buyers history for this type of relevant information and makes sperate column or space for that person called ''recommended'' on that online website which includes the stuff which user likes.]]> 2021-09-03 10:15:32 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1714988747 faizan3536 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1715074861 2021-09-03 11:52:18 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1715074861 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1715078275 In online shopping websites, machines play the roles of giving us suggestions. It does that by recording items previously purchased by other people. When we are new to an online shopping website, it gives us the suggestions from earlier purchases. Simply, it records earlier purchases and suggests new accounts. The cookies play the next role of storing our details and give suggestions to us when already logged in. The cookies record our purchases and the machine passes them on to new accounts.]]> 2021-09-03 11:55:41 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1715078275 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1715095871 For detection of fraudulent activity, machines are trained using algorithms involving real purchasing behavior of the user. First, it conducts a survey and then redundant the data which is a very important process. They are tested and modified if they do not follow given criteria]]> 2021-09-03 12:09:42 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1715095871 umar6693 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1716542868 First the data in the emails is collected  through a machine learning algorithm. Then all the data is cleaned by removing the stop words such as 'the', and 'a' leaving behind only the important data behind. Certain words or phrases for example, lottery, earn, full-refund, are detected which tell that this email is most likely to be a spam email. The machine learning system learns from past emails which are known to be spam.]]> 2021-09-04 11:39:49 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1716542868 umar6693 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1716591543 First of all data is gathered through a survey or web- scraping. Then the unnecessary data is removed but this needs to be done very carefully to ensure that the possibility of wrong predictions is low. The algorithm is trained through real customer behaviours and then based on that learning a model is built which allows the machine to detect fraudulent activity for example, the spending of an unusual amount of money or on a piece of jewellery, it is most likely to be a fraud.]]> 2021-09-04 13:10:14 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1716591543 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1717198176 The machine learning in this application stores data from previous spam emails by taking the keywords like lottery as data and when some spam email is approached they compare the keywords if many of them are matched it gets to know it is a spam email.]]> 2021-09-05 07:22:57 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1717198176 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1717198849 Machine learning in recognizing user buyer history works via collaboration filtering, which is the process of predicting a new customer's buying habit by comparing it with other buyers. As such, if person A buys a book and a workbook, 2 weeks later Person B may also buy the same book, and the machine will suggest the workbook due to its past experiences and linking.
This is particularly common in creating music playlists.]]> 2021-09-05 07:24:08 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1717198849 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1717200014 Machine learning is able to detect fraudulent activity by comparing the new action with the base examples stored in it already. First it collects the data. Then it will separately analyze all components of the data, comparing it with its training for tracing fraudulent data, that teaches it how to recognize faulty stuff]]> 2021-09-05 07:25:57 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1717200014 hadi6494 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1718732778 Algorithms use pre-defined rules in the form of a regular expression to give a score to the messages present in the e-mails. Based on the scores generated, they segregate emails into spam non-spam categories.Algorithms extract the incoming mails' features and create a multi-dimensional space vector and draw points for every new instance. Based on the KNN algorithm, these new points get assigned to the closest class of spam and non-spam.]]> 2021-09-06 06:54:27 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1718732778 hadi6494 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1718734874 This is done using collaboration filtering in which if two customers have the same shopping behaviours, they are shown a similar type of shopping list to fit their interests or needs which the machine learns with its past experiences of other customers. The cookies record our purchases and the machine passes them on to new accounts.]]> 2021-09-06 06:55:30 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1718734874 hadi6494 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1718735861 it is able to detect fraudluent activity by activity by comparing the new action with base examples stored. it will then separately analyze all components of the data, comparing with training for tracing fraudulent data , that teaches hoe to find faulty things.]]> 2021-09-06 06:56:02 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1718735861 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1724892527 Several studies have been carried out on machine learning techniques and many of these algorithms are being applied in the field of email spam filtering. Examples of such algorithms include Deep Learning, Naïve Bayes, Support Vector Machines, Neural Networks, K-Nearest Neighbour, Rough sets, and Random Forests.
These ML techniques have the capacity to learn and identify spam mails and phishing messages by analyzing loads of such messages throughout a vast collection of computers. Since machine learning have the capacity to adapt to varying conditions, Gmail and Yahoo mail spam filters do more than just checking junk emails using pre-existing rules. They generate new rules themselves based on what they have learnt as they continue in their spam filtering operation.

]]> 2021-09-08 13:40:55 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1724892527 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1724902244 Collaborative filtering is a technique that can filter out items that a user might like on the basis of reactions by similar users. It works by searching a large group of people and finding a smaller set of users with tastes similar to a particular user.]]> 2021-09-08 13:43:22 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1724902244 https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1724909483 Machine learning models are able to learn from patterns of normal behavior. They are very fast to adapt to changes in that normal behaviour and can quickly identify patterns of fraud transactions. This means that the model can identify suspicious customers even when there hasn't been a chargeback yet.]]> 2021-09-08 13:45:35 UTC https://padlet.com/tchr68019/46bzz5teghdmo6z0/wish/1724909483