Loan Prediction Github
" (Doshi-Velez and Kim 2017 5). I am providing you link here, that will help you. Found only on the islands of New Zealand, the Weka is a flightless bird with an inquisitive nature. Clone via HTTPS Clone with Git or checkout with SVN using the repository's web address. It does so by predicting next words in a text given a history of previous words. Explore current and past security and utility token offerings. New to web design and PHP scripts? Check out the Free tutorials section for articles that teach you a little about FTP, CHMOD, pasting code into your HTML pages and more. TL;DR - Learn how to evolve a population of simple organisms each containing a unique neural network using a genetic algorithm. csv at line number 39788, 39789, 39790. Unchained Capital offers cash loans to long-term cryptocurrency holders in a secure, fast, and transparent manner, backed by our multisignature cold storage custody solution. Flexible Data Ingestion. The Company is obligated to use commercially reasonable efforts to service and collect the Loans in accordance with industry standards and consistent with the terms of the LRO Agreement. You can find the data science accelerator for credit risk prediction on GitHub. You may view all data sets through our searchable interface. js is an easy way to include animated, interactive graphs on your website for free. The Ethereum-based prediction platform Gnosis has done so much for the blockchain community already in launching its DutchX smart contracts, the Gnosis Safe, and the Gnosis Olympia Alpha — thus creating the tools with which others can launch their own marketplaces. In the beginning price at 9609 Dollars. Deployed the Final solution as a Web application (Restful API), Link for demo : default-risk. I am trying to plot a ROC curve to evaluate the accuracy of a prediction model I developed in Python using logistic regression packages. Imbalanced datasets spring up everywhere. But, I disagree with Monica Anderson’s answer: it is NOT the “only” approach. us, a database of bills in the U. Their GitHub is a hub for pop culture data. The LROs Covered by this Offering Circular. Clone this repo to your computer. Created a user interface to the blockchain back-end using React and Drizzle. Now consider a lender with no intention to consider race, but who uses neighborhood average income as a signal of creditworthiness. Evolving Simple Organisms using a Genetic Algorithm and Deep Learning from Scratch with Python. This page provides the latest reported value for - Italy Loans to Private Sector - plus previous releases, historical high and low, short-term forecast and long-term prediction, economic calendar, survey consensus and news. I am going to talk about how to create a pipeline which can help ingest the data from the flat files, re-run the predictions for the incremental data. ETHLend will either create a prediction market on ETHLend or partner with third party prediction market provider (such as Augur or Gnosis) for providing a prediction market on loan repayments. Lend and earn interests. -John Keats. The crypto industry would undoubtedly benefit from the creation of a stable cryptocurrency. To learn more about how SHAP works in practice, we applied it to predicting loan defaults in data from Lending Club. Tip: you can also follow us on Twitter. Learning to Embed Songs and Tags for Playlist Prediction. I think you should start solving on your own but as you have asked help hence I'd like you to search on GIthub. org and archive-it. The loans are used for farm improvements like seed, to cover household expenses like school fees and maize flour when coffee income is low, and even to buy land. In this project, we aim at finding a good model which can accurately predict whether a loan applicant would default in the future or not. Skip to content. However, it makes cryptocurrencies virtually useless when it comes to mainstream use – like for loans, salaries, and other basic financial contracts. The digital tokes ensure repayment of the loan, and lenders can lend Ether without the loss of capital. Trade on the outcome of an upcoming election, hedge against natural disasters and market crashes. Learn about importing data from a source, viewing parsed data, viewing job details and dataset summaries, and more to predict bad loans with H2O Flow AutoML. rdl" for example provides an overview of the R runtime parameters and gives you an option to configure your instance with a button click. But insurance also requires another kind of trust. Knowledge is your reward. 7 train Models By Tag. Designed and built the Ethereum smart contracts forming the back-end of the platform. transform(test) evaluator. Well, we’ve done that for you right here. A charged off loan is a loan that is declared by a creditor (usually a lending institution) that an amount of debt is unlikely to be collected, usually when the loan repayment is severely delinquent by the debtor. However, if he/she doesn’t repay the loan, then the lender loses money. , information about the customer as he or she exists right now. The demand for housing also depends on the wealth of households, their current income, and interest rates. us, a database of bills in the U. Most importantly, you must convert your data type to numeric, otherwise this algorithm won't work. Gagan has 7 jobs listed on their profile. Multi-space Probabilistic Sequence Modeling. the goal of this Experiment is to predict the repayment rate for the student loans. advisers are Dr. The higher the score, the higher is the probability of the loan getting charged-off in the future. Get App & Earn Now. Examples: March Madness predictions, political polling, the Bachelorette show, etc. This is a good “unclean” data set which needed a lot of data manipulation before try building a model. Loan Default Prediction – Imperial College London. See the complete profile on LinkedIn and discover Gagan’s. Takes the test features and use the rules of each randomly created decision tree to predict the oucome and stores the predicted outcome (target). Bytecoin price chart | OnChainFX. So, let's take a three-year loan means I pay back within three years. The report "R Services - Configuration. Reinforcement Learning is one of the fields I’m most excited about. us, a database of bills in the U. But, I disagree with Monica Anderson’s answer: it is NOT the “only” approach. Mortgage Transition Model Based on LoanPerformance Data By Shuyao Yang Master of Arts in Statistics Washington University in St. New to web design and PHP scripts? Check out the Free tutorials section for articles that teach you a little about FTP, CHMOD, pasting code into your HTML pages and more. I am trying to plot a ROC curve to evaluate the accuracy of a prediction model I developed in Python using logistic regression packages. To demonstrate a typical workflow, we’ll introduce you to a few personas. ’ Financial compensation data and aggregate email statistics from the Enron Corpus were used as features for prediction. BigML Education Videos BigML offers a wide variety of basic Machine Learning resources that can be composed together to solve complex Machine Learning tasks. Note that you can have n hidden layers, with the term "deep" learning implying multiple hidden layers. All the projects including the following can be found on my Github. (Keep in mind that the knn() function wants a ‘clean’ training and test data frames, i. Real Estate Price Prediction. Below is the step wise step solution of the problem with which I achieved Rank 960 on the Public Leaderboard…. Even though this is an Analytics Vidhya competition, my goal in this project is not to compete or to construct the most accurate model but to. Documentation for the caret package. However, it makes cryptocurrencies virtually useless when it comes to mainstream use – like for loans, salaries, and other basic financial contracts. RAPIDS Team at NVIDIA. Prediction Markets Decentralized prediction markets and cryptodervivative platforms generate sets of tokens that represent a financial stake in the outcomes of events. Flexible Data Ingestion. Installation Download the data. Do It Right. Available rates and terms are subject to change and may vary based on loan amount, qualifications, and collateral profile. set_args() set_mode() Change elements of a model specification. Practice problems or data science projects are one of the best ways to learn data science. Project Motivation The loan is one of the most important products of the banking. The value of a loan is thus tied to assessments of the value of the collateral (car, home, business, artwork, etc…), the likely level of future inflation, and predictions about overall economic growth. Explore current and past security and utility token offerings. The BlockFi lets you put your crypto to work and earn monthly interest payments in the asset-type that you deposit with BlockFi. Other terms, conditions, and restrictions may apply. Job Description. the loan's balance, its delinquency status, and whether it prepaid. Loan Predict Service. The models below are available in train. Bagging is a way to decrease the variance in the prediction by generating additional data for training from dataset using combinations with repetitions to produce multi-sets of the original data. This capability now enables our customers to have near real-time predictive analytics. BTC to USD predictions for November 2019. Loan Default Prediction at Kaggle. You can invest BitConnect coin in Bitconnect lending platform exclusively from the BitConnect Dashboard. Logistic regression is a generalized linear model that we can use to model or predict categorical outcome variables. We’ll be using publicly available data from LendingClub. Figure 2: Boxplots of interest rate vs. The report "R Services - Configuration. One example is the generation of structural default prediction models (e. $100M custodial insurance. Keras Tutorial: Keras is a powerful easy-to-use Python library for developing and evaluating deep learning models. 9 minute read. Hi, I am new to data science world. Optional: If you want, you can also download SSMS custom reports available on github. Investors (lenders) provide loans to borrowers in exchange for the promise of repayment with interest. Explore current and past security and utility token offerings. Using probabilities lets you guess the most probable class, but you can also order the predictions with respect to being part of that class. Use this category for discussions related to Loan prediction practice problems. We'll be using publicly available data from LendingClub. A charged off loan is a loan that is declared by a creditor (usually a lending institution) that an amount of debt is unlikely to be collected, usually when the loan repayment is severely delinquent by the debtor. the loan's balance, its delinquency status, and whether it prepaid. Below, you’ll find a curated list of free datasets for data science and machine learning, organized by their use case. As has become my tradition now for nigh-on a decade, I will first go back over last years’ predictions, to see how well I called it (and keep me honest), then wax prophetic on what I think the new year has to offer us. To learn more about how SHAP works in practice, we applied it to predicting loan defaults in data from Lending Club. May 21, 2015. Explore Popular Topics Like Government, Sports, Medicine, Fintech, Food, More. ery loan in a bucket, take A2 for example, has exactly the same risk, which is why assigning them the same rate of interest doesn't quite make sense. Prosper, a peer-to-peer lending marketplace, makes their loan data available to the public. When you borrow or lend, you normally do so in dollar terms. We can now use the training set to classify an unknown case (Age=48 and Loan=$142,000) using Euclidean distance. $100M custodial insurance. Data Scientists use computer science applications, modelling, statistics, analytics, and math to uncover insights in data sets. Investors (lenders) provide loans to borrowers in exchange for the promise of repayment with interest. Loan Prediction Problem Problem Statement About Company Dream Housing Finance company deals in all home loans. and international economic data, graphs and other data-related tools, plus quality research from St. #I created a model to predict the approval of home loans. 1 Importance of Interpretability. It is common in credit scoring to classify bad accounts as those which have ever had a 60 day delinquency or. Based on the data, machine learning model predicts the pickup demand of cabs in 10 minutes time frame. So, when the predicted value is measured as a probability, use Logistic Regression. Peer-to-peer lending is disrupting the banking industry since it directly connects borrowers and potential lenders/investors. The LROs Covered by this Offering Circular. can download our cleaned dataset from github of prediction accuracy. use a two layered LSTM architecture coupled with a dense output layer to make a prediction. Rank 2 solution and description by HelloWorld. RAPIDS Team at NVIDIA. System Requirement Specifications Assignment 1 Sample Solution Page 5 5. A framework to quickly build a predictive model in under 10 minutes using Python & create a benchmark solution for data science competitions. 1 In this chapter, we first look at the link between loans and options and subsequently investigate how this link can be used to. Explore current and past security and utility token offerings. One of the tables in this data is the Listing data, which contains details about every loan request submitted to the Prosper marketplace. I have never seen this before, and do not know where to start in terms of trying to sort out the issue. The value of a loan is thus tied to assessments of the value of the collateral (car, home, business, artwork, etc…), the likely level of future inflation, and predictions about overall economic growth. Providing free U. The portal offers a wide variety of state of the art problems like - image classification, customer churn, prediction, optimization, click prediction, NLP and many more. I think you should start solving on your own but as you have asked help hence I'd like you to search on GIthub. Loan Prediction. Xgboost is short for eXtreme Gradient Boosting package. Notice: Undefined index: HTTP_REFERER in /home/forge/carparkinc. Real Estate Price Prediction. Find real-time UNH - UnitedHealth Group Inc stock quotes, company profile, news and forecasts from CNN Business. Machine learning algorithm trains on a dataset to make predictions. The index is updated once a month. The company wants to automate the loan eligibility process (real time) based on customer detail provided while filling online application form. Put your functions into a file with an intuitive name,. 1: radhan55: 0. • Lifetime Value prediction – Derive LTV predictions by combining expected survival times with monthly revenues Transforming Data • Active customers – Predict each customer’s time to next purchase, and use to identify “active” vs. The data attributes include student grades, demographic, social and school related features) and it was collected by using school reports and questionnaires. Mortgage Transition Model Based on LoanPerformance Data By Shuyao Yang Master of Arts in Statistics Washington University in St. Underwriters are responsible for making an on-chain prediction as to the probability that a borrower will repay his loan in full. Customer churn impacts the cost to the business, for example, lost revenue and the marketing costs involved with replacing those customers with new ones. The new fec. Home Credit Group Loan Risk Prediction 11 Oct 2018 - python, data cleaning, and prediction. In the previous posts in our portfolio series, we talked about how to build a storytelling project , how to create a data science blog , how to create a machine learning project , and how to. Cross Chain trading, P2P exchange and P2P loans, staking, instant trading, zero risk investments, insurance and a lot more features. Sign up No description or website provided. Reinforcement Learning is one of the fields I’m most excited about. 6 Available Models. Charging off a loan is the last resort that the bank will do on a severely delinquent loan, with the prediction data at hand, the loan officer could offer personalized incentives like lower interest rate or longer repayment period to help customers to keep making loan payments and thus prevent the loan of getting charged off. A Machine Learning Approach for Tracking and Predicting Student Performance in Degree Programs Jie Xu, Member, IEEE, Kyeong Ho Moon, Student Member, IEEE, and Mihaela van der Schaar, Fellow, IEEE Abstract—Accurately predicting students' future performance based on their ongoing academic records is crucial for effectively. GitHub Gist: star and fork mohinigupta125's gists by creating an account on GitHub. Filled with fun financial calculations and models. Learning to Embed Songs and Tags for Playlist Prediction. prediction with limited user activity data, while it also provides valuable insights into the reasons behind user churn, which can be leveraged to fundamentally improve retention (Section 4). In this example, we consider a loan. Reinforcement Learning is one of the fields I’m most excited about. In our second case study for this course, loan default prediction, you will tackle financial data, and predict when a loan is likely to be risky or safe for the bank. 06 EUR Billion in the fourth quarter of 1998 and a record low of 171. Cryptocurrency Market & Coin Exchange report, prediction for the future: You'll find the Electra Price prediction below. Loan prediction (Analytics Vidhya). Contribute to ParthS007/Loan-Approval-Prediction development by creating an account on GitHub. Decentralized lending platforms provide loans to business or the public with no intermediaries are present. This page provides the latest reported value for - Indonesia Loan Growth - plus previous releases, historical high and low, short-term forecast and long-term prediction, economic calendar, survey consensus and news. RuTroll A chrome extension which detects and highlights if a tweet is likely to be published from a Russian troll or not. So I googled it. The expected loss is defined by the following equation:. The bad loans did not pay as intended. Skip to content. Company wants to automate the loan eligibility process (real time) based on customer detail provided while filling online application form. Charging off a loan is the last resort that the bank will do on a severely delinquent loan, with the prediction data at hand, the loan officer could offer personalized incentives like lower interest rate or longer repayment period to help customers to keep making loan payments and thus prevent the loan of getting charged off. The client's business goal is to improve it's decision-making criteria for approving new loans. Learn about importing data from a source, viewing parsed data, viewing job details and dataset summaries, and more to predict bad loans with H2O Flow AutoML. Loans that indicate good repayment behavior are considered “good” and loans that indicate less than perfect repayment behavior are considered “bad”. To achieve both, we not only have to ensure good prediction accuracy of good and bad credit ratings, we also need to minimize the mis. Fannie Mae acquires loans from other lenders as a way of inducing them to lend more. PHP projects with source code free download from PHP Tutorial for Students and many more php projects. ) Feed the previous prediction back into the input window by moving it one step forward and then predict at the current time step. It’s a great list for browsing, importing into our platform, creating new models and just exploring what. This weekend I found myself in a particularly drawn-out game of Chutes and Ladders with my four-year-old. I think you should start solving on your own but as you have asked help hence I'd like you to search on GIthub. This data set is related with a mortgage loan and challenge is to predict approval status of loan (Approved/ Reject). MarketWatch provides the latest stock market, financial and business news. describe the product characteristics like interest rate, loan amount, loan term etc. View Peyman Heidari’s profile on LinkedIn, the world's largest professional community. Loans to Private Sector in Germany averaged 1109. Predict whether or not loans acquired by Fannie Mae will go into foreclosure. evaluate(predictions) 0. The Grade and Sub-grade of a Loan application would be determined based on the credit report of the applicant. This is what the term "churn modeling" most often refers to, and is the definition we will adhere to in this post. Skip to content. The value of a loan is thus tied to assessments of the value of the collateral (car, home, business, artwork, etc…), the likely level of future inflation, and predictions about overall economic growth. ABC institute provides best Java, Software Testing, Python, Machine Learning, Full Stack training courses with placement in Bangalore, Hyderabad, Vijayawada. Created Dec 30, 2018. He's an outspoken critic of Vitalik Buterin, stating that "it's hard to see how his invention has made any difference, beyond inflating the crypto bubble. Can any one help me with the explanation please? Hackathons. Reinforcement Learning is one of the fields I’m most excited about. All gists Back to GitHub. Loan Chargeoff Prediction using SQL Server 2016 R Services – Using DSVM with SQL Server 2016 and Microsoft ML, this solution template walks through how to create and clean up a set of simulated data, use 5 different models to train, select the best performant model, perform scoring using the model and save the prediction results back to SQL. While we don't know the context in which John Keats mentioned this, we are sure about its implication in data science. The effect of loan length and number of credit inquiries on interest rates is summarized in Figure 2 below. (Asuncion et al, 2007). In this post I will analyze loan prediction model using Logistic Regression algorithm and evaluate it using LogLoss function. Loan Chargeoff Prediction using SQL Server 2016 R Services - Using DSVM with SQL Server 2016 and Microsoft ML, this solution template walks through how to create and clean up a set of simulated data, use 5 different models to train, select the best performant model, perform scoring using the model and save the prediction results back to SQL. Github nbviewer. default_pred <- predict(nb_default, test, type="class") predict will, by default, return the class with the highest probability for that predicted row. gov makes it easier than ever to find what you need to know about the federal campaign finance process. The estimate affects every part of your daily life, such as getting a loan or how long you have to wait for a new passport. Loan Chargeoff Prediction using SQL Server 2016 R Services – Using DSVM with SQL Server 2016 and Microsoft ML, this solution template walks through how to create and clean up a set of simulated data, use 5 different models to train, select the best performant model, perform scoring using the model and save the prediction results back to SQL. As complex models become widely used, it's more important than ever to have ways of understanding them. That means the lender only makes profit (interest) if the borrower pays off the loan. In the first notebook I tackled the null data. Risk prediction and monitoring is critical for the success of the business model. Law and Artificial Intelligence Jack Balkin, Rebecca Crootof, Bethany Hill, Anat Lior, & George Wang Spring 2018 This reading group will explore topics at the intersection of Law and Artificial Intelligence. There entires in these lists are arguable. Volatility is great for making headlines and keeping investors interested. an open auto loan and mortgage on a credit report, following a tra c stop. In this example, we use Loan data to predict charge off loans, we use R Scoring Engine to predict "bad" loans. Loan Prediction Problem Problem Statement About Company Dream Housing Finance company deals in all home loans. There is a companion website too. Customer first apply for home loan after that company validates the. Thus credit limit value is not constant, but is predictor in the forecasting equations. In this article, you are going to learn the most popular classification algorithm. The collection is organized into three main parts: the input layer, the hidden layer, and the output layer. Loan Term: Period over which a loan agreement is in force, and before or at the end of which the loan should either be repaid or renegotiated for another term. See what you qualify for in minutes, with no impact to your credit score. In contrast, a soft classification indicates the confidence the model has in its prediction. Loan Predict Service. 6 means “Man, that’s a tough call, but I’m gonna go with yes, you can sell that cookie,” while a value exactly in the. Random forest prediction pseudocode: To perform prediction using the trained random forest algorithm uses the below pseudocode. Machine learning is a particular approach to artificial intelligence. Flexible Data Ingestion. Download Open Datasets on 1000s of Projects + Share Projects on One Platform. The new fec. There entires in these lists are arguable. json metadata in Project Open Data. The data covers the. These variables and many others would allow us to arrive at a \better" model P[makes-loan-payment] = e + X: (1) Finally we have arrived at a model capable of fooling someone! We could. js is an easy way to include animated, interactive graphs on your website for free. Project Posters and Reports, Fall 2017. It’s that time of year again… well, actually, a few days late, but I’ve been busy, I swear. There are 22 columns with 600K rows. code is available in a github repo. You can also import genderPredictor into your own code and run the methods manually. 06 EUR Billion in the fourth quarter of 1998 and a record low of 171. You will be amazed to see the speed of this algorithm against comparable models. Data Set Information: This data approach student achievement in secondary education of two Portuguese schools. 9305555556:. AI empowers organizations to self-manage their network regardless of scale and complexity, and predicts network failures and security attacks. Sign up No description or website provided. This page provides the latest reported value for - Indonesia Loan Growth - plus previous releases, historical high and low, short-term forecast and long-term prediction, economic calendar, survey consensus and news. Join GitHub today. You may view all data sets through our searchable interface. Last but not the least, to demonstrate the predictive power of the dataset, this section presents an application of logistic regression to estimate the expected loss using the segmented data on loans whose status are listed as 'Current'. Our model will predict an outcome of 1 for Fully Paid loans, and 0 for Charged Off loans. Flexible Data Ingestion. Smart contracts can revolutionize the traditional lending system. The construction and study of algorithms that can learn from and make predictions on data The creation of a model from example inputs in order to make data-driven predictions or decisions Learning from experience either with or without supervision from humans. Github nbviewer. There are many ways of imputing missing data - we could delete those rows, set the values to 0, etc. Built a prototype of real estate-backed loans platform. Predict whether or not loans acquired by Fannie Mae will go into foreclosure. Meanwhile, borrowers can pay lower interest rates than they would pay on a bank loan. Creating contrastive explanations is application-dependent because it requires a point of reference for comparison. Tip: you can also follow us on Twitter. 90 EUR Billion in the second quarter of 2019 from 1513. As previously mentioned, objects produced by the train function contain the “optimized” model in the finalModel sub-object. Litecoin Price Prediction If you still haven’t gotten the point, Litecoin has an extremely bright future and so will you if you plan to bang that super hot latina that you jerk off to. Also remember, the public LB is a bit deceptive its only using 50% of the data not all , so you might overfit here but final ranking is on the remaining 50%. It was introduced into Congress on May 9, 2019. Bitcoin price forecast at the end of the month $9003, change for October -6. Now consider a lender with no intention to consider race, but who uses neighborhood average income as a signal of creditworthiness. Web; Images; Videos; News; About; Privacy; Terms; Contact Us © 2019 InfoSpace Holdings LLC. A statistician advised our Bank Manager to use Logistic regression Why not use linear regression? Least squares regression can cause impossible estimates such as probabilities that are less than zero and greater than 1. On the other hand, if the feature is categorical, then the first subplot is count plot and the second subplot is based on the group_by loan_status classes. Guillaume is a Kaggle expert specialized in ML and AI. This loan prediction problem of Analytics Vidhya is my first ever data science project. TensorFlow offers APIs for beginners and experts to develop for desktop, mobile, web, and cloud. Sheikh Khaled Ghafoor. " His Ethereum prediction is that the ETH value is approaching its rightful price: zero. Regression Analysis: A Complete Example This section works out an example that includes all the topics we have discussed so far in this chapter. Fig1: clip from movie zootopia. Loans that indicate good repayment behavior are considered “good” and loans that indicate less than perfect repayment behavior are considered “bad”. Salt Lending LLC's loans are issued pursuant to private agreements. Explore Popular Topics Like Government, Sports, Medicine, Fintech, Food, More. Download Open Datasets on 1000s of Projects + Share Projects on One Platform. 8 minute read. A PowerBI report will also walk through the analysis and trend of credit loans and prediction of chargeoff probability. Flexible Data Ingestion. This model was created by: - Starting with the "Prosper Listings (1yr 20130205)" dataset. Even though this is an Analytics Vidhya competition, my goal in this project is not to compete or to construct the most accurate model but to. After creating the naive Bayes model object, you can use the universal predict function to create a prediction. The LROs Covered by this Offering Circular. Predicting with Naive Bayes Classifier. The LROs Covered by this Offering Circular. If the y argument to this function is a factor, the random sampling occurs within each class and should preserve the overall class distribution of the data. Clearly these are not the best predictions, but the model is definitely able to pick up on trends in the data, without the use of any feature engineering. Find real-time UNH - UnitedHealth Group Inc stock quotes, company profile, news and forecasts from CNN Business. Or copy & paste this link into an email or IM:. Investing in BitConnect Lending. As has become my tradition now for nigh-on a decade, I will first go back over last years’ predictions, to see how well I called it (and keep me honest), then wax prophetic on what I think the new year has to offer us. Sign in Sign up Loan_Id and Loan_Status (prediction). Training a Logistic Regression for loan credit risk prediction is a standard practice in the Credit Score industry. It is common in credit scoring to classify bad accounts as those which have ever had a 60 day delinquency or. Survival analysis is used to analyze or predict when an event is likely to happen. In our second case study for this course, loan default prediction, you will tackle financial data, and predict when a loan is likely to be risky or safe for the bank. If, on the other hand, the duration of the bank’s liabilities is 10 years, its liabilities will decrease −2 × 10 = −20% or $19 million and the bank will profit from the interest rate rise. Augur is an open-source prediction & forecasting market platform that allows anyone to forecast events and get rewarded for predicting them correctly. That means the lender only makes profit (interest) if the borrower pays off the loan. This is a post exploring one of the oldest prediction problems--predicting risk on consumer loans. Estimate predictions using the k-NN algorithm and the three predictors. Ravencoin (RVN) is an open-source blockchain project that specializes in the creation and peer-to-peer transfer of assets. Peer-to-peer lending is disrupting the banking industry since it directly connects borrowers and potential lenders/investors.