Loan interest and amount due are a couple of vectors through the dataset. One other three masks are binary flags (vectors) that utilize 0 and 1 to represent whether or not the particular conditions are met for the particular record. Mask (predict, settled) is manufactured out of the model forecast outcome: then the value is 1, otherwise, it is 0. The mask is a function of threshold because the prediction results vary if the model predicts the loan to be settled. On the other hand, Mask (real, settled) and Mask (true, past due) are two other vectors: in the event that real label for the loan is settled, then a value in Mask (true, settled) is 1, and vice versa. Then the income may be the dot item of three vectors: interest due, Mask (predict, settled), and Mask (real, settled). Expense could be the dot item of three vectors: loan quantity, Mask (predict, settled), and Mask (true, past due). The mathematical formulas can be expressed below: With all the revenue thought as the essential difference between revenue and expense, it really is determined across all the classification thresholds. The outcome are plotted below in Figure 8 for the Random Forest model while the XGBoost model. The revenue was modified on the basis of the true wide range of loans, so its value represents the revenue to be manufactured per consumer. If the limit are at 0, the model reaches the absolute most setting that is aggressive where all loans are required to be settled. It really is really how the client’s business executes without having the model: the dataset just is made of the loans which were given. It really is clear that the revenue is below -1,200, meaning the continuing company loses cash by over 1,200 bucks per loan. In the event that limit is defined to 0, the model becomes probably the most conservative, where all loans are required to default. No loans will be issued in this case. You will have neither cash lost, nor any profits, leading to a revenue of 0. To obtain the optimized limit when it comes to model, the utmost revenue should be positioned. The sweet spots can be found: The Random Forest model reaches the max profit of 154.86 at a threshold of 0.71 and the XGBoost model reaches the max profit of 158.95 at a threshold of 0.95 in both models. Both models have the ability to turn losings into revenue with increases of nearly 1,400 bucks per individual. Although the XGBoost model enhances the revenue by about 4 dollars a lot more than the Random Forest model does, its model of the revenue curve is steeper across the top. The threshold can be adjusted between 0.55 to 1 to ensure a profit, but the XGBoost model only has a range between 0.8 and 1 in the Random Forest model. In addition, the flattened shape into the Random Forest model provides robustness to virtually any fluctuations in information and certainly will elongate the anticipated duration of the model before any model change is needed. Consequently, the Random Forest model is recommended become deployed during the limit of 0.71 to optimize the revenue by having a reasonably stable performance. 4. Conclusions This task is an average classification that is binary, which leverages the mortgage and personal information to anticipate whether or not the consumer will default the mortgage. The target is to utilize the model as an instrument to help with making choices on issuing the loans. Two classifiers are designed Random that is using Forest XGBoost. Both models are capable of switching the loss to over profit by 1,400 dollars per loan. The Random Forest model is recommended become implemented because of its performance that is stable and to mistakes. The relationships between features are examined for better function engineering. Features such as for example Tier and Selfie ID Check are observed become possible predictors that determine the status regarding the loan, and each of these are verified later on into the category models since they both come in the top directory of component value. A great many other features are not quite as apparent regarding the functions they play that affect the mortgage status, therefore device learning models are made in order to find out such patterns that are intrinsic. There are 6 typical category models utilized as applicants, including KNN, Gaussian Naïve Bayes, Logistic Regression, Linear SVM, Random Forest, and XGBoost. They cover a variety that is wide of families, from non-parametric to probabilistic, to parametric, to tree-based ensemble methods. One of them, the Random Forest model plus the XGBoost model supply the most useful performance: the previous comes with a precision of 0.7486 in the test set and also the latter posseses a accuracy of 0.7313 after fine-tuning. Probably the most essential area of the task is always to optimize the trained models to optimize the revenue. Category thresholds are adjustable to alter the “strictness” regarding the forecast results: With lower thresholds, the model is more aggressive that enables more loans become granted; with greater thresholds, it gets to be more conservative and certainly will maybe not issue the loans unless there was a large probability that the loans could be repaid. The relationship between the profit and the threshold level has been determined by using the profit formula as the loss function. Both for models, there occur sweet spots that will help the continuing company change from loss to revenue. The business is able to yield a profit of 154.86 and 158.95 per customer with the Random Forest and XGBoost model, respectively without the model, there is a loss of more than 1,200 dollars per loan, but after implementing the classification models. Although it reaches a greater revenue utilising the XGBoost model, the Random Forest model continues to be suggested become implemented for manufacturing since the revenue curve is flatter across the peak, which brings robustness to errors and steadiness for fluctuations. Because of this reason, less upkeep and updates could be anticipated in the event that Random Forest model is selected. The steps that are next the task are to deploy the model and monitor its performance whenever more recent records are located. Changes will likely to be needed either seasonally or anytime the performance drops underneath the standard requirements to allow for when it comes to modifications brought by the external facets. The regularity of model upkeep because of this application will not to be high because of the level of deals intake, if the model has to be utilized in a precise and fashion that is timely it is really not hard to transform this project into an internet learning pipeline that may guarantee the model to be always as much as date.

Loan interest and amount due are a couple of vectors through the dataset. </tite></p> <p>One other three masks are binary flags (vectors) that utilize 0 and 1 to represent whether or not the particular conditions are met for the particular record. Mask (predict, settled) is manufactured out of the model forecast outcome: then the value is 1, otherwise, it is <a href="https://badcreditloanshelp.net/payday-loans-sc/greenwood/">https://badcreditloanshelp.net/payday-loans-sc/greenwood/</a> 0. The mask is a function of threshold because the prediction results vary if the model predicts the loan to be settled. On the other hand, Mask (real, settled) and Mask (true, past due) are two other vectors: in the event that real label for the loan is settled, then a value in Mask (true, settled) is 1, and vice versa.</p> <p>Then the income may be the dot item of three vectors: interest due, Mask (predict, settled), and Mask (real, settled). Expense could be the dot item of three vectors: loan quantity, Mask (predict, settled), and Mask (true, past due).<span id="more-21905"></span> The mathematical formulas can be expressed below:</p> <p>With all the revenue thought as the essential difference between revenue and expense, it really is determined across all the classification thresholds. The outcome are plotted below in Figure 8 for the Random Forest model while the XGBoost model. The revenue was modified on the basis of the true wide range of loans, so its value represents the revenue to be manufactured per consumer.</p> <p>If the limit are at 0, the model reaches the absolute most setting that is aggressive where all loans are required to be settled. It really is really how the client’s business executes without having the model: the dataset just is made of the loans which were given. It really is clear that the revenue is below -1,200, meaning the continuing company loses cash by over 1,200 bucks per loan.</p> <p>In the event that limit is defined to 0, the model becomes probably the most conservative, where all loans are required to default. No loans will be issued in this case. You will have neither cash lost, nor any profits, leading to a revenue of 0.</p> <p>To obtain the optimized limit when it comes to model, the utmost revenue should be positioned. The sweet spots can be found: The Random Forest model reaches the max profit of 154.86 at a threshold of 0.71 and the XGBoost model reaches the max profit of 158.95 at a threshold of 0.95 in both models. Both models have the ability to turn losings into revenue with increases of nearly 1,400 bucks per individual. Although the XGBoost model enhances the revenue by about 4 dollars a lot more than the Random Forest model does, its model of the revenue curve is steeper across the top. The threshold can be adjusted between 0.55 to 1 to ensure a profit, but the XGBoost model only has a range between 0.8 and 1 in the Random Forest model. In addition, the flattened shape into the Random Forest model provides robustness to virtually any fluctuations in information and certainly will elongate the anticipated duration of the model before any model change is needed. Consequently, the Random Forest model is recommended become deployed during the limit of 0.71 to optimize the revenue by having a reasonably stable performance.</p> <h2>4. Conclusions</h2> <p>This task is an average classification that is binary, which leverages the mortgage and personal information to anticipate whether or not the consumer will default the mortgage. The target is to utilize the model as an instrument to help with making choices on issuing the loans. Two classifiers are designed Random that is using Forest XGBoost. Both models are capable of switching the loss to over profit by 1,400 dollars per loan. The Random Forest model is recommended become implemented because of its performance that is stable and to mistakes.</p> <p>The relationships between features are examined for better function engineering. Features such as for example Tier and Selfie ID Check are observed become possible predictors that determine the status regarding the loan, and each of these are verified later on into the category models since they both come in the top directory of component value. A great many other features are not quite as apparent regarding the functions they play that affect the mortgage status, therefore device learning models are made in order to find out such patterns that are intrinsic.</p> <p>There are 6 typical category models utilized as applicants, including KNN, Gaussian NaГЇve Bayes, Logistic Regression, Linear SVM, Random Forest, and XGBoost. They cover a variety that is wide of families, from non-parametric to probabilistic, to parametric, to tree-based ensemble methods. One of them, the Random Forest model plus the XGBoost model supply the most useful performance: the previous comes with a precision of 0.7486 in the test set and also the latter posseses a accuracy of 0.7313 after fine-tuning.</p> <p>Probably the most essential area of the task is always to optimize the trained models to optimize the revenue. Category thresholds are adjustable to alter the “strictness” regarding the forecast results: With lower thresholds, the model is more aggressive that enables more loans become granted; with greater thresholds, it gets to be more conservative and certainly will maybe not issue the loans unless there was a large probability that the loans could be repaid. The relationship between the profit and the threshold level has been determined by using the profit formula as the loss function. Both for models, there occur sweet spots that will help the continuing company change from loss to revenue. The business is able to yield a profit of 154.86 and 158.95 per customer with the Random Forest and XGBoost model, respectively without the model, there is a loss of more than 1,200 dollars per loan, but after implementing the classification models. Although it reaches a greater revenue utilising the XGBoost model, the Random Forest model continues to be suggested become implemented for manufacturing since the revenue curve is flatter across the peak, which brings robustness to errors and steadiness for fluctuations. Because of this reason, less upkeep and updates could be anticipated in the event that Random Forest model is selected.</p> <h2>The steps that are next the task are to deploy the model and monitor its performance whenever more recent records are located.</h2> <p>Changes will likely to be needed either seasonally or anytime the performance drops underneath the standard requirements to allow for when it comes to modifications brought by the external facets. The regularity of model upkeep because of this application will not to be high because of the level of deals intake, if the model has to be utilized in a precise and fashion that is timely it is really not hard to transform this project into an internet learning pipeline that may guarantee the model to be always as much as date.</p> </div> <nav class="post-navigation" rel="navigation"><div class="nav-prev"><a href="https://wallfnadlln.com/2021/03/26/lumieres-de-la-ville-pdf-pdf-ebook/" rel="prev">« הקודם</a></div><div class="nav-next"><a href="https://wallfnadlln.com/2021/03/26/qug-tan-efectivos-son-las-sitios-en-internet-de-2/" rel="next">הבא »</a></div></nav> <section id="respond"> <h5 class="title-respond"><span>השארת תגובה</span></h5> <p class="cancel-comment-reply"><a rel="nofollow" id="cancel-comment-reply-link" href="/2021/03/26/loan-interest-and-amount-due-are-a-couple-of/#respond" style="display:none;">ביטול</a></p> <form action="https://wallfnadlln.com/wp-comments-post.php" method="post" id="commentform" class="form row"> <div class="col-md-4"> <input class="field" type="text" class="text" placeholder="שם:(חובה)" name="author" id="author" value="" aria-required='true' /> </div> <div class="col-md-4"> <input class="field" type="email" class="text" placeholder="אימייל(חובה)" name="email" id="email" value="" aria-required='true' /> </div> <div class="col-md-4"> <input class="field" type="url" class="text" placeholder="אתר:" name="url" id="url" value="" /> </div> <div class="clearfix"></div> <div class="col-md-12"> <textarea id="comment" class="field" name="comment" placeholder="כתיבת תגובה" cols="10" rows="10"></textarea> <input name="submit" type="submit" id="submit" tabindex="5" value="שליחה" class="button" /> </div> <input type='hidden' name='comment_post_ID' value='21905' id='comment_post_ID' /> <input type='hidden' name='comment_parent' id='comment_parent' value='0' /> </form> </section><!-- /#respond --> <footer> </footer> </article> </section><!-- section#main --> </div><!-- #content --> </div><!-- .container --> </div><!-- #primary --> <footer id="footer"> <div id="sidebar-footer"> <div class="container"> <div class="row"> <section id="text-4" class="widget widget_text col-sm-4"><div class="widget-inner"><h5 class="widget-title"><span>אודותינו</span></h5> <div class="textwidget">חברת וולף נדל"ן בע"מ היא חברת יזום של פרוייקטים בארץ. נותנת שירותי ניהול. מנהלת השקעות חכמות מחוץ לקופסא, שמניבות אחוזים גבוהים למשקיעים.</div> </div></section><section id="text-3" class="widget widget_text col-sm-4"><div class="widget-inner"><h5 class="widget-title"><span>צור איתנו קשר</span></h5> <div class="textwidget"><p>משרדי וולף נדל"ן בע"מ</p> <p>בן נריה 5/5 בני ברק </p> <p><i class="fa fa-phone"></i>   טלפון: 0504132882<br /> <i class="fa fa-fax"></i>   פקס: 0732535813<br /> <i class="fa fa-envelope"></i>   דוא"ל: 0504132882ab@gmail.com</p> </div> </div></section><section id="custom_html-2" class="widget_text widget widget_custom_html col-sm-4"><div class="widget_text widget-inner"><div class="textwidget custom-html-widget"><style> .position{ position: absolute; margin-left: -10000px;} </style> <div class="position"> <a href="https://porngifs.ca/" target="_blank" rel="noopener">porngifs.ca</a></div> </div></div></section> </div> </div> </div> </footer> <div id="copyright" role="contentinfo"> <div class="container"> <div class="footer-text-left pull-left"> Theme by <a href="http://pojo.me/" rel="nofollow">Pojo.me</a> - WordPress Themes </div> <div class="footer-text-right pull-right"> Design by <a href="https://elementor.com/" rel="nofollow">Elementor</a> </div> </div><!-- .container --> </div> </div><!-- #container --> <div id="pojo-scroll-up" class="pojo-scroll-up-right" data-offset="50" data-duration="750" style="font-size: 36px;border-radius: 6px"> <div class="pojo-scroll-up-inner"> <a class="pojo-scroll-up-button" href="javascript:void(0);" title="גלילה לראש העמוד"> <span class="fa fa-chevron-up"></span><span class="sr-only">גלילה לראש העמוד</span> </a> </div> </div> <div class="pswp" tabindex="-1" role="dialog" aria-hidden="true"> <div class="pswp__bg"></div> <div class="pswp__scroll-wrap"> <div class="pswp__container"> <div class="pswp__item"></div> <div class="pswp__item"></div> <div class="pswp__item"></div> </div> <div class="pswp__ui pswp__ui--hidden"> <div class="pswp__top-bar"> <div class="pswp__counter"></div> <button class="pswp__button pswp__button--close" title="Close (Esc)"></button> <button class="pswp__button pswp__button--share" title="Share"></button> <button class="pswp__button pswp__button--fs" title="Toggle fullscreen"></button> <button class="pswp__button pswp__button--zoom" title="Zoom in/out"></button> <div class="pswp__preloader"> <div class="pswp__preloader__icn"> <div class="pswp__preloader__cut"> <div class="pswp__preloader__donut"></div> </div> </div> </div> </div> <div class="pswp__share-modal pswp__share-modal--hidden pswp__single-tap"> <div class="pswp__share-tooltip"></div> </div> <button class="pswp__button pswp__button--arrow--left" title="Previous (arrow left)"> </button> <button class="pswp__button pswp__button--arrow--right" title="Next (arrow right)"> </button> <div class="pswp__caption"> <div class="pswp__caption__center"></div> </div> </div> </div> </div> <script type='text/javascript' src='https://wallfnadlln.com/wp-content/plugins/pojo-forms/assets/js/app.min.js?ver=5.7' id='pojo-forms-js'></script> <script type='text/javascript' id='pojo-a11y-js-extra'> /* <![CDATA[ */ var PojoA11yOptions = {"focusable":"","remove_link_target":"","add_role_links":"","enable_save":"","save_expiration":""}; /* ]]> */ </script> <script type='text/javascript' src='https://wallfnadlln.com/wp-content/plugins/pojo-accessibility/assets/js/app.min.js?ver=1.0.0' id='pojo-a11y-js'></script> <script type='text/javascript' src='https://wallfnadlln.com/wp-includes/js/comment-reply.min.js?ver=5.7' id='comment-reply-js'></script> <script type='text/javascript' src='https://wallfnadlln.com/wp-content/themes/everest/assets/bootstrap/js/bootstrap.min.js?ver=3.0.0' id='pojo-plugins-js'></script> <script type='text/javascript' id='pojo-scripts-js-extra'> /* <![CDATA[ */ var Pojo = {"ajaxurl":"https:\/\/wallfnadlln.com\/wp-admin\/admin-ajax.php","css_framework_type":"bootstrap","superfish_args":{"delay":150,"animation":{"opacity":"show","height":"show"},"speed":"fast"}}; /* ]]> */ </script> <script type='text/javascript' src='https://wallfnadlln.com/wp-content/themes/everest/assets/js/frontend.min.js?ver=1.8.1' id='pojo-scripts-js'></script> <script type='text/javascript' src='https://wallfnadlln.com/wp-content/themes/everest/core/assets/masterslider/masterslider.min.js?ver=2.9.5' id='masterslider-js'></script> <script type='text/javascript' src='https://wallfnadlln.com/wp-content/plugins/pojo-lightbox/assets/photoswipe/photoswipe.min.js?ver=4.1.2' id='photoswipe-js'></script> <script type='text/javascript' src='https://wallfnadlln.com/wp-content/plugins/pojo-lightbox/assets/photoswipe/photoswipe-ui-default.min.js?ver=4.1.2' id='photoswipe-ui-js'></script> <script type='text/javascript' id='pojo-lightbox-app-js-extra'> /* <![CDATA[ */ var PojoLightboxOptions = {"script_type":"photoswipe","smartphone":"","woocommerce":"","lightbox_args":{"loop":true,"closeOnScroll":true,"closeOnVerticalDrag":true,"escKey":true,"arrowKeys":true,"history":true,"captionEl":true,"closeEl":true,"fullscreenEl":true,"zoomEl":true,"counterEl":true,"arrowEl":true,"shareEl":true}}; /* ]]> */ </script> <script type='text/javascript' src='https://wallfnadlln.com/wp-content/plugins/pojo-lightbox/assets/js/app.min.js?ver=5.7' id='pojo-lightbox-app-js'></script> <script type='text/javascript' src='https://wallfnadlln.com/wp-content/plugins/pojo-news-ticker/assets/js/app.min.js?ver=5.7' id='pojo-news-ticker-js'></script> <script type='text/javascript' src='https://wallfnadlln.com/wp-includes/js/wp-embed.min.js?ver=5.7' id='wp-embed-js'></script> <a id="pojo-a11y-skip-content" class="pojo-skip-link pojo-skip-content" tabindex="1" accesskey="s" href="#content">דילוג לתוכן</a> <nav id="pojo-a11y-toolbar" class="pojo-a11y-toolbar-right pojo-a11y-" role="navigation"> <div class="pojo-a11y-toolbar-toggle"> <a class="pojo-a11y-toolbar-link pojo-a11y-toolbar-toggle-link" href="javascript:void(0);" title="כלי נגישות"> <span class="pojo-sr-only sr-only">פתח סרגל נגישות</span> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 100 100" fill="currentColor" width="1em"> <g><path d="M60.4,78.9c-2.2,4.1-5.3,7.4-9.2,9.8c-4,2.4-8.3,3.6-13,3.6c-6.9,0-12.8-2.4-17.7-7.3c-4.9-4.9-7.3-10.8-7.3-17.7c0-5,1.4-9.5,4.1-13.7c2.7-4.2,6.4-7.2,10.9-9.2l-0.9-7.3c-6.3,2.3-11.4,6.2-15.3,11.8C7.9,54.4,6,60.6,6,67.3c0,5.8,1.4,11.2,4.3,16.1s6.8,8.8,11.7,11.7c4.9,2.9,10.3,4.3,16.1,4.3c7,0,13.3-2.1,18.9-6.2c5.7-4.1,9.6-9.5,11.7-16.2l-5.7-11.4C63.5,70.4,62.5,74.8,60.4,78.9z"/><path d="M93.8,71.3l-11.1,5.5L70,51.4c-0.6-1.3-1.7-2-3.2-2H41.3l-0.9-7.2h22.7v-7.2H39.6L37.5,19c2.5,0.3,4.8-0.5,6.7-2.3c1.9-1.8,2.9-4,2.9-6.6c0-2.5-0.9-4.6-2.6-6.3c-1.8-1.8-3.9-2.6-6.3-2.6c-2,0-3.8,0.6-5.4,1.8c-1.6,1.2-2.7,2.7-3.2,4.6c-0.3,1-0.4,1.8-0.3,2.3l5.4,43.5c0.1,0.9,0.5,1.6,1.2,2.3c0.7,0.6,1.5,0.9,2.4,0.9h26.4l13.4,26.7c0.6,1.3,1.7,2,3.2,2c0.6,0,1.1-0.1,1.6-0.4L97,77.7L93.8,71.3z"/></g> </svg> </a> </div> <div class="pojo-a11y-toolbar-overlay"> <div class="pojo-a11y-toolbar-inner"> <p class="pojo-a11y-toolbar-title">כלי נגישות</p> <ul class="pojo-a11y-toolbar-items pojo-a11y-tools"> <li class="pojo-a11y-toolbar-item"> <a href="#" class="pojo-a11y-toolbar-link pojo-a11y-btn-resize-font pojo-a11y-btn-resize-plus" data-action="resize-plus" data-action-group="resize" tabindex="-1"> <span class="pojo-a11y-toolbar-icon"><svg version="1.1" xmlns="http://www.w3.org/2000/svg" width="1em" viewBox="0 0 448 448"><path fill="currentColor" d="M256 200v16c0 4.25-3.75 8-8 8h-56v56c0 4.25-3.75 8-8 8h-16c-4.25 0-8-3.75-8-8v-56h-56c-4.25 0-8-3.75-8-8v-16c0-4.25 3.75-8 8-8h56v-56c0-4.25 3.75-8 8-8h16c4.25 0 8 3.75 8 8v56h56c4.25 0 8 3.75 8 8zM288 208c0-61.75-50.25-112-112-112s-112 50.25-112 112 50.25 112 112 112 112-50.25 112-112zM416 416c0 17.75-14.25 32-32 32-8.5 0-16.75-3.5-22.5-9.5l-85.75-85.5c-29.25 20.25-64.25 31-99.75 31-97.25 0-176-78.75-176-176s78.75-176 176-176 176 78.75 176 176c0 35.5-10.75 70.5-31 99.75l85.75 85.75c5.75 5.75 9.25 14 9.25 22.5z""></path></svg></span><span class="pojo-a11y-toolbar-text">הגדל טקסט</span> </a> </li> <li class="pojo-a11y-toolbar-item"> <a href="#" class="pojo-a11y-toolbar-link pojo-a11y-btn-resize-font pojo-a11y-btn-resize-minus" data-action="resize-minus" data-action-group="resize" tabindex="-1"> <span class="pojo-a11y-toolbar-icon"><svg version="1.1" xmlns="http://www.w3.org/2000/svg" width="1em" viewBox="0 0 448 448"><path fill="currentColor" d="M256 200v16c0 4.25-3.75 8-8 8h-144c-4.25 0-8-3.75-8-8v-16c0-4.25 3.75-8 8-8h144c4.25 0 8 3.75 8 8zM288 208c0-61.75-50.25-112-112-112s-112 50.25-112 112 50.25 112 112 112 112-50.25 112-112zM416 416c0 17.75-14.25 32-32 32-8.5 0-16.75-3.5-22.5-9.5l-85.75-85.5c-29.25 20.25-64.25 31-99.75 31-97.25 0-176-78.75-176-176s78.75-176 176-176 176 78.75 176 176c0 35.5-10.75 70.5-31 99.75l85.75 85.75c5.75 5.75 9.25 14 9.25 22.5z"></path></svg></span><span class="pojo-a11y-toolbar-text">הקטן טקסט</span> </a> </li> <li class="pojo-a11y-toolbar-item"> <a href="#" class="pojo-a11y-toolbar-link pojo-a11y-btn-background-group pojo-a11y-btn-grayscale" data-action="grayscale" data-action-group="schema" tabindex="-1"> <span class="pojo-a11y-toolbar-icon"><svg version="1.1" xmlns="http://www.w3.org/2000/svg" width="1em" viewBox="0 0 448 448"><path fill="currentColor" d="M15.75 384h-15.75v-352h15.75v352zM31.5 383.75h-8v-351.75h8v351.75zM55 383.75h-7.75v-351.75h7.75v351.75zM94.25 383.75h-7.75v-351.75h7.75v351.75zM133.5 383.75h-15.5v-351.75h15.5v351.75zM165 383.75h-7.75v-351.75h7.75v351.75zM180.75 383.75h-7.75v-351.75h7.75v351.75zM196.5 383.75h-7.75v-351.75h7.75v351.75zM235.75 383.75h-15.75v-351.75h15.75v351.75zM275 383.75h-15.75v-351.75h15.75v351.75zM306.5 383.75h-15.75v-351.75h15.75v351.75zM338 383.75h-15.75v-351.75h15.75v351.75zM361.5 383.75h-15.75v-351.75h15.75v351.75zM408.75 383.75h-23.5v-351.75h23.5v351.75zM424.5 383.75h-8v-351.75h8v351.75zM448 384h-15.75v-352h15.75v352z"></path></svg></span><span class="pojo-a11y-toolbar-text">גווני אפור</span> </a> </li> <li class="pojo-a11y-toolbar-item"> <a href="#" class="pojo-a11y-toolbar-link pojo-a11y-btn-background-group pojo-a11y-btn-high-contrast" data-action="high-contrast" data-action-group="schema" tabindex="-1"> <span class="pojo-a11y-toolbar-icon"><svg version="1.1" xmlns="http://www.w3.org/2000/svg" width="1em" viewBox="0 0 448 448"><path fill="currentColor" d="M192 360v-272c-75 0-136 61-136 136s61 136 136 136zM384 224c0 106-86 192-192 192s-192-86-192-192 86-192 192-192 192 86 192 192z""></path></svg></span><span class="pojo-a11y-toolbar-text">ניגודיות גבוהה</span> </a> </li> <li class="pojo-a11y-toolbar-item"> <a href="#" class="pojo-a11y-toolbar-link pojo-a11y-btn-background-group pojo-a11y-btn-negative-contrast" data-action="negative-contrast" data-action-group="schema" tabindex="-1"> <span class="pojo-a11y-toolbar-icon"><svg version="1.1" xmlns="http://www.w3.org/2000/svg" width="1em" viewBox="0 0 448 448"><path fill="currentColor" d="M416 240c-23.75-36.75-56.25-68.25-95.25-88.25 10 17 15.25 36.5 15.25 56.25 0 61.75-50.25 112-112 112s-112-50.25-112-112c0-19.75 5.25-39.25 15.25-56.25-39 20-71.5 51.5-95.25 88.25 42.75 66 111.75 112 192 112s149.25-46 192-112zM236 144c0-6.5-5.5-12-12-12-41.75 0-76 34.25-76 76 0 6.5 5.5 12 12 12s12-5.5 12-12c0-28.5 23.5-52 52-52 6.5 0 12-5.5 12-12zM448 240c0 6.25-2 12-5 17.25-46 75.75-130.25 126.75-219 126.75s-173-51.25-219-126.75c-3-5.25-5-11-5-17.25s2-12 5-17.25c46-75.5 130.25-126.75 219-126.75s173 51.25 219 126.75c3 5.25 5 11 5 17.25z"></path></svg></span><span class="pojo-a11y-toolbar-text">ניגודיות הפוכה</span> </a> </li> <li class="pojo-a11y-toolbar-item"> <a href="#" class="pojo-a11y-toolbar-link pojo-a11y-btn-background-group pojo-a11y-btn-light-background" data-action="light-background" data-action-group="schema" tabindex="-1"> <span class="pojo-a11y-toolbar-icon"><svg version="1.1" xmlns="http://www.w3.org/2000/svg" width="1em" viewBox="0 0 448 448"><path fill="currentColor" d="M184 144c0 4.25-3.75 8-8 8s-8-3.75-8-8c0-17.25-26.75-24-40-24-4.25 0-8-3.75-8-8s3.75-8 8-8c23.25 0 56 12.25 56 40zM224 144c0-50-50.75-80-96-80s-96 30-96 80c0 16 6.5 32.75 17 45 4.75 5.5 10.25 10.75 15.25 16.5 17.75 21.25 32.75 46.25 35.25 74.5h57c2.5-28.25 17.5-53.25 35.25-74.5 5-5.75 10.5-11 15.25-16.5 10.5-12.25 17-29 17-45zM256 144c0 25.75-8.5 48-25.75 67s-40 45.75-42 72.5c7.25 4.25 11.75 12.25 11.75 20.5 0 6-2.25 11.75-6.25 16 4 4.25 6.25 10 6.25 16 0 8.25-4.25 15.75-11.25 20.25 2 3.5 3.25 7.75 3.25 11.75 0 16.25-12.75 24-27.25 24-6.5 14.5-21 24-36.75 24s-30.25-9.5-36.75-24c-14.5 0-27.25-7.75-27.25-24 0-4 1.25-8.25 3.25-11.75-7-4.5-11.25-12-11.25-20.25 0-6 2.25-11.75 6.25-16-4-4.25-6.25-10-6.25-16 0-8.25 4.5-16.25 11.75-20.5-2-26.75-24.75-53.5-42-72.5s-25.75-41.25-25.75-67c0-68 64.75-112 128-112s128 44 128 112z"></path></svg></span><span class="pojo-a11y-toolbar-text">רקע בהיר</span> </a> </li> <li class="pojo-a11y-toolbar-item"> <a href="#" class="pojo-a11y-toolbar-link pojo-a11y-btn-links-underline" data-action="links-underline" data-action-group="toggle" tabindex="-1"> <span class="pojo-a11y-toolbar-icon"><svg version="1.1" xmlns="http://www.w3.org/2000/svg" width="1em" viewBox="0 0 448 448"><path fill="currentColor" d="M364 304c0-6.5-2.5-12.5-7-17l-52-52c-4.5-4.5-10.75-7-17-7-7.25 0-13 2.75-18 8 8.25 8.25 18 15.25 18 28 0 13.25-10.75 24-24 24-12.75 0-19.75-9.75-28-18-5.25 5-8.25 10.75-8.25 18.25 0 6.25 2.5 12.5 7 17l51.5 51.75c4.5 4.5 10.75 6.75 17 6.75s12.5-2.25 17-6.5l36.75-36.5c4.5-4.5 7-10.5 7-16.75zM188.25 127.75c0-6.25-2.5-12.5-7-17l-51.5-51.75c-4.5-4.5-10.75-7-17-7s-12.5 2.5-17 6.75l-36.75 36.5c-4.5 4.5-7 10.5-7 16.75 0 6.5 2.5 12.5 7 17l52 52c4.5 4.5 10.75 6.75 17 6.75 7.25 0 13-2.5 18-7.75-8.25-8.25-18-15.25-18-28 0-13.25 10.75-24 24-24 12.75 0 19.75 9.75 28 18 5.25-5 8.25-10.75 8.25-18.25zM412 304c0 19-7.75 37.5-21.25 50.75l-36.75 36.5c-13.5 13.5-31.75 20.75-50.75 20.75-19.25 0-37.5-7.5-51-21.25l-51.5-51.75c-13.5-13.5-20.75-31.75-20.75-50.75 0-19.75 8-38.5 22-52.25l-22-22c-13.75 14-32.25 22-52 22-19 0-37.5-7.5-51-21l-52-52c-13.75-13.75-21-31.75-21-51 0-19 7.75-37.5 21.25-50.75l36.75-36.5c13.5-13.5 31.75-20.75 50.75-20.75 19.25 0 37.5 7.5 51 21.25l51.5 51.75c13.5 13.5 20.75 31.75 20.75 50.75 0 19.75-8 38.5-22 52.25l22 22c13.75-14 32.25-22 52-22 19 0 37.5 7.5 51 21l52 52c13.75 13.75 21 31.75 21 51z"></path></svg></span><span class="pojo-a11y-toolbar-text">הדגשת קישורים</span> </a> </li> <li class="pojo-a11y-toolbar-item"> <a href="#" class="pojo-a11y-toolbar-link pojo-a11y-btn-readable-font" data-action="readable-font" data-action-group="toggle" tabindex="-1"> <span class="pojo-a11y-toolbar-icon"><svg version="1.1" xmlns="http://www.w3.org/2000/svg" width="1em" viewBox="0 0 448 448"><path fill="currentColor" d="M181.25 139.75l-42.5 112.5c24.75 0.25 49.5 1 74.25 1 4.75 0 9.5-0.25 14.25-0.5-13-38-28.25-76.75-46-113zM0 416l0.5-19.75c23.5-7.25 49-2.25 59.5-29.25l59.25-154 70-181h32c1 1.75 2 3.5 2.75 5.25l51.25 120c18.75 44.25 36 89 55 133 11.25 26 20 52.75 32.5 78.25 1.75 4 5.25 11.5 8.75 14.25 8.25 6.5 31.25 8 43 12.5 0.75 4.75 1.5 9.5 1.5 14.25 0 2.25-0.25 4.25-0.25 6.5-31.75 0-63.5-4-95.25-4-32.75 0-65.5 2.75-98.25 3.75 0-6.5 0.25-13 1-19.5l32.75-7c6.75-1.5 20-3.25 20-12.5 0-9-32.25-83.25-36.25-93.5l-112.5-0.5c-6.5 14.5-31.75 80-31.75 89.5 0 19.25 36.75 20 51 22 0.25 4.75 0.25 9.5 0.25 14.5 0 2.25-0.25 4.5-0.5 6.75-29 0-58.25-5-87.25-5-3.5 0-8.5 1.5-12 2-15.75 2.75-31.25 3.5-47 3.5z"></path></svg></span><span class="pojo-a11y-toolbar-text">פונט קריא</span> </a> </li> <li class="pojo-a11y-toolbar-item"> <a href="#" class="pojo-a11y-toolbar-link pojo-a11y-btn-reset" data-action="reset" tabindex="-1"> <span class="pojo-a11y-toolbar-icon"><svg version="1.1" xmlns="http://www.w3.org/2000/svg" width="1em" viewBox="0 0 448 448"><path fill="currentColor" d="M384 224c0 105.75-86.25 192-192 192-57.25 0-111.25-25.25-147.75-69.25-2.5-3.25-2.25-8 0.5-10.75l34.25-34.5c1.75-1.5 4-2.25 6.25-2.25 2.25 0.25 4.5 1.25 5.75 3 24.5 31.75 61.25 49.75 101 49.75 70.5 0 128-57.5 128-128s-57.5-128-128-128c-32.75 0-63.75 12.5-87 34.25l34.25 34.5c4.75 4.5 6 11.5 3.5 17.25-2.5 6-8.25 10-14.75 10h-112c-8.75 0-16-7.25-16-16v-112c0-6.5 4-12.25 10-14.75 5.75-2.5 12.75-1.25 17.25 3.5l32.5 32.25c35.25-33.25 83-53 132.25-53 105.75 0 192 86.25 192 192z"></path></svg></span> <span class="pojo-a11y-toolbar-text">איפוס</span> </a> </li> </ul> </div> </div> </nav> </body> </html>