Loymax, 2026
From version 8.1
edited by Andrej Rylov
on 2025/10/22 11:21
Change comment: There is no comment for this version
To version 6.1
edited by Andrej Rylov
on 2025/10/22 11:10
Change comment: Upload new image "Recom_02.png", version 1.1

Summary

Details

Page properties
Content
... ... @@ -5,7 +5,7 @@
5 5  {{toc depth="3" start="2"/}}
6 6  )))
7 7  
8 -=== **General information** ===
8 +=== **General Information** ===
9 9  
10 10  **Product recommendations** are a tool for creating effective customer communications via email campaigns, as well as widgets on the website and in the Mobile Application.
11 11  
... ... @@ -38,7 +38,7 @@
38 38  * The Product Recommendations module is an optional, separately licensed feature available on a paid basis.
39 39  )))
40 40  
41 -=== **Interaction of Loymax infrastructure components for generating product recommendations** ===
41 +=== **Interaction of Loymax Infrastructure Components for Generating Product Recommendations** ===
42 42  
43 43  Data sources for receipts, customers, and products from the product catalog used to generate product recommendations include the **DWH BI** data warehouse and/or the **ClickHouse SmartCom** database management system. This data is transferred to the **Loymax AI** module, where it is processed and product recommendations are calculated using ML algorithms. The resulting recommendations are then delivered via API to **data marts**. The **API-proxy server** validates incoming requests and formats responses for Smart Communications. **Smart Communications** retrieves responses from the **API-proxy server**, enriches them with data (images, product names, links, prices, etc.), inserts them into predefined templates, and sends mass messagings containing the generated product recommendations to customers.
44 44  
... ... @@ -104,9 +104,9 @@
104 104  1. Mobile Application,
105 105  1. Personal Account.
106 106  
107 -=== **{{id name="01"/}}**Popular Products** algorithm** ===
107 +=== **{{id name="01"/}}“Popular Products” Algorithm** ===
108 108  
109 -==== 1. Description of the Popular Products algorithm ====
109 +==== 1. Description of the **Popular Products** Algorithm ====
110 110  
111 111  The **Popular Products** algorithm calculates a ranking across the [[entire*>>doc:||anchor="Star"]] product list. It recommends the top-N most popular products from each category based on each product’s position in the overall ranking.
112 112  This approach recommends a broader range of products (i.e., several items from different categories), which is preferable for achieving business goals.
... ... @@ -113,8 +113,10 @@
113 113  Product rankings are calculated based on total units sold across all customer purchases—i.e., the most purchased items.
114 114  **All purchases** include both online and offline transactions processed through Loymax.
115 115  
116 -==== 2. Use cases for the Popular Products algorithm in personalized campaigns ====
116 +==== 2. Use Cases for the **Popular Products** Algorithm in Personalized Campaigns ====
117 117  
118 +**Email Campaigns:**
119 +
118 118  (% class="table-bordered" style="width:1218px" %)
119 119  (% class="info" %)|(% style="text-align:center; width:399px" %)**Campaign**|(% style="text-align:center; width:370px" %)**Trigger**|(% style="text-align:center; width:446px" %)**Use Case**
120 120  |(% style="width:399px" %)[[**Abandoned View**>>doc:Main.Usage.Smart_Communications.Campaign_list.Triggers.WebHome||anchor="H41144043E44843543D43D44B43943F44043E44143C43E442440"]]|(% style="width:370px" %)Product viewed but not purchased|(% style="width:446px" %)(((
... ... @@ -133,7 +133,7 @@
133 133  After a defined time interval (t), send a reminder email about the abandoned cart along with the most popular products.
134 134  )))
135 135  
136 -==== (% style="color:inherit; font-family:Montserrat,sans-serif; font-size:20px; font-weight:600" %)3. Examples of using the (% style="color:inherit; font-family:Montserrat,sans-serif; font-size:20px" %)Popular Products(% style="color:inherit; font-family:Montserrat,sans-serif; font-size:20px; font-weight:600" %) algorithm for website personalization(%%) ====
138 +(% style="color:inherit; font-family:Montserrat,sans-serif; font-size:20px; font-weight:600" %)3. Examples of Using the (% style="color:inherit; font-family:Montserrat,sans-serif; font-size:20px" %)**Popular Products**(% style="color:inherit; font-family:Montserrat,sans-serif; font-size:20px; font-weight:600" %) Algorithm for Website Personalization
137 137  
138 138  (% class="table-bordered" style="width:1218px" %)
139 139  (% class="info" %)|(% style="text-align:center; width:399px" %)**Campaign**|(% style="text-align:center; width:370px" %)**Trigger**|(% style="text-align:center; width:446px" %)**Use Case**
... ... @@ -144,15 +144,15 @@
144 144  |(% style="width:399px" %)[[**Current Category Page View**>>doc:Main.Usage.Smart_Communications.Campaign_list.Triggers.WebHome||anchor="H41A43B43843543D44243F43E44143C43E44244043543B43F44043E43444343A44243E43244344E43A43044243543343E44043844EA043D430441430439442435"]]|(% style="width:370px" %)Category view|(% style="width:446px" %)**Popular Products** section.
145 145  Customer is browsing a category. The most popular products are displayed.
146 146  
147 -==== 4. General concept of the Popular Products algorithm ====
149 +==== 4. General Concept of the **Popular Products** Algorithm ====
148 148  
149 149  **Example**: Generating recommendations by selecting the top 1 most popular product from each category.
150 150  
151 151  |(% style="border-color:#ffffff; text-align:center" %)[[image:attach:Recommendations_01.png]]
152 152  
153 -=== **{{id name="02"/}}Popular Products in Category algorithm** ===
155 +=== **{{id name="02"/}}“Popular Products in Category” Algorithm** ===
154 154  
155 -==== 1. Description of the Popular Products in Category algorithm ====
157 +==== 1. Description of the **Popular Products in Category** Algorithm ====
156 156  
157 157  The **Popular Products in Category** algorithm calculates a popularity ranking among products within each specific category.
158 158  
... ... @@ -161,18 +161,20 @@
161 161  Product rankings are calculated based on total units sold across all customer purchases—i.e., the most purchased items.
162 162  **All purchases** include both online and offline transactions processed through Loymax.
163 163  
164 -==== 2. Use cases for the Popular Products in Category algorithm in personalized campaigns ====
166 +==== 2. Use Cases for the **Popular Products in Category** Algorithm in Personalized Campaigns ====
165 165  
166 166  Recommended products are selected based on the customer’s previously viewed/ordered/purchased items and the category (i.e., category ID) to which those items belong.
167 167  
168 168  The category/classifier level assigned to a product can be either the lowest or a higher level in the hierarchy.
169 169  
172 +**Email Campaigns:**
173 +
170 170  (% class="table-bordered" style="width:1218px" %)
171 171  (% class="info" %)|(% style="text-align:center; width:399px" %)**Campaign**|(% style="text-align:center; width:370px" %)**Trigger**|(% style="text-align:center; width:446px" %)**Use Case**
172 172  |(% style="width:399px" %)[[**Abandoned View**>>doc:Main.Usage.Smart_Communications.Campaign_list.Triggers.WebHome||anchor="H41144043E44843543D43D44B43943F44043E44143C43E442440"]]|(% style="width:370px" %)Product viewed but not purchased|(% style="width:446px" %)Send an email after X days recommending the most popular products in the same category.
173 173  |(% style="width:399px" %)[[**Abandoned Cart**>>doc:Main.Usage.Smart_Communications.Campaign_list.Triggers.WebHome||anchor="H41144043E44843543D43D43044F43A43E44043743843D430"]]|(% style="width:370px" %)Product added to cart but not purchased|(% style="width:446px" %)Send an email after X days recommending the most popular products in the same category.
174 174  
175 -==== 3. Use cases for the Popular Products in Category algorithm in website personalization ====
179 +==== 3. Use Cases for the **Popular Products in Category** Algorithm in Website Personalization ====
176 176  
177 177  Recommended products are selected based on the customer’s on-site behavior (event tracking) and the category (i.e., category ID) of the viewed product. The classifier level (i.e., category) can be configured—it may be the lowest level or a higher-level category.
178 178  
... ... @@ -181,7 +181,7 @@
181 181  |(% style="width:399px" %)[[**Current Product Page View**>>doc:Main.Usage.Smart_Communications.Campaign_list.Triggers.WebHome||anchor="H41A43B43843543D44243F43E44143C43E44244043543B43F44043E43444343A442A043D430441430439442435"]]|(% style="width:369px" %)Product view|(% style="width:447px" %)**Compared With This Product** section.
182 182  Recommend popular products from the same category based on the currently viewed item.
183 183  
184 -==== 4. General concept of the algorithm ====
188 +==== 4. General Concept of the Algorithm ====
185 185  
186 186  Product rankings are calculated at each classifier level (**Group ID**, **Subgroup ID**, **Category ID**) across all products belonging to that hierarchical level—i.e., all items in the group/subgroup/category—regardless of deeper nesting.
187 187  
... ... @@ -191,22 +191,24 @@
191 191  
192 192  |(% style="border-color:#ffffff; text-align:center" %)[[image:attach:Recom_02.png]]
193 193  
194 -=== **{{id name="03"/}}Similar Products algorithm** ===
198 +=== **{{id name="03"/}}“Similar Products” Algorithm** ===
195 195  
196 -==== 1. Description of the Similar Products algorithm ====
200 +==== 1. Description of the **Similar Products** Algorithm ====
197 197  
198 198  The **Similar Products** algorithm recommends alternative [[products*>>doc:||anchor="Star"]] that are the most similar to the viewed/ordered/purchased item.
199 199  
200 200  It recommends N products that have similar attributes to the viewed/ordered/purchased product.
201 201  
202 -==== 2. Use cases for the Similar Products algorithm in personalized campaigns ====
206 +==== 2. Use Cases for the **Similar Products** Algorithm in Personalized Campaigns ====
203 203  
208 +**Email Campaigns:**
209 +
204 204  (% class="table-bordered" style="width:1218px" %)
205 205  (% class="info" %)|(% style="text-align:center; width:399px" %)**Campaign**|(% style="text-align:center; width:370px" %)**Trigger**|(% style="text-align:center; width:446px" %)**Use Case**
206 206  |(% style="width:399px" %)[[**Abandoned View**>>doc:Main.Usage.Smart_Communications.Campaign_list.Triggers.WebHome||anchor="H41144043E44843543D43D44B43943F44043E44143C43E442440"]]|(% style="width:370px" %)Product viewed but not ordered|(% style="width:446px" %)Send an email after X days with alternative products similar to those viewed by the customer.
207 207  |(% style="width:399px" %)[[**Abandoned Cart**>>doc:Main.Usage.Smart_Communications.Campaign_list.Triggers.WebHome||anchor="H41144043E44843543D43D43044F43A43E44043743843D430"]]|(% style="width:370px" %)Product added to cart but not purchased|(% style="width:446px" %)Send an email after X days with alternative products similar to those viewed by the customer.
208 208  
209 -==== 3. Use cases for the Similar Products algorithm in website personalization ====
215 +==== 3. Use Cases for the **Similar Products** Algorithm in Website Personalization ====
210 210  
211 211  (% class="table-bordered" style="width:1218px" %)
212 212  (% class="info" %)|(% style="text-align:center; width:399px" %)**Campaign**|(% style="text-align:center; width:369px" %)**Trigger**|(% style="text-align:center; width:447px" %)**Use Case**
... ... @@ -213,7 +213,7 @@
213 213  |(% style="width:399px" %)[[**Current Product Page View**>>doc:Main.Usage.Smart_Communications.Campaign_list.Triggers.WebHome||anchor="H41A43B43843543D44243F43E44143C43E44244043543B43F44043E43444343A442A043D430441430439442435"]]|(% style="width:369px" %)Product view|(% style="width:447px" %)**You Might Like** section.
214 214  Recommend alternative products similar to the one currently viewed by the customer.
215 215  
216 -==== 4. General concept of the algorithm ====
222 +==== 4. General Concept of the Algorithm ====
217 217  
218 218  |(% style="border-color:white; width:368px" %)[[image:attach:ARL_rules_example.gif]]|(% style="border-color:white; width:1070px" %)(((
219 219  For each product, a neural network generates an N-dimensional vector representation (embedding) based on product descriptions, attributes, purchase/view statistics/content.
... ... @@ -225,14 +225,16 @@
225 225  Similar products are selected based on minimal cosine distance between vectors—i.e., those sharing the most similar combination of product attributes.
226 226  )))
227 227  
228 -=== **{{id name="04"/}}Bought Together algorithm** ===
234 +=== **{{id name="04"/}}“Bought Together” Algorithm** ===
229 229  
230 -==== 1. Description of the Bought Together algorithm ====
236 +==== 1. Description of the **Bought Together** Algorithm ====
231 231  
232 232  The **Bought Together** algorithm recommends products that most frequently appear in the same transaction as the viewed/ordered/purchased items.
233 233  
234 -==== 2. Use cases for the Bought Together algorithm in personalized campaigns ====
240 +==== 2. Use Cases for the **Bought Together** Algorithm in Personalized Campaigns ====
235 235  
242 +**Email Campaigns:**
243 +
236 236  (% class="table-bordered" style="width:1218px" %)
237 237  (% class="info" %)|(% style="text-align:center; width:399px" %)**Campaign**|(% style="text-align:center; width:370px" %)**Trigger**|(% style="text-align:center; width:446px" %)**Use Case**
238 238  |(% style="width:399px" %)[[**Abandoned View**>>doc:Main.Usage.Smart_Communications.Campaign_list.Triggers.WebHome||anchor="H41144043E44843543D43D44B43943F44043E44143C43E442440"]]|(% style="width:370px" %)Product viewed but not ordered|(% style="width:446px" %)Send an email after X days with products most frequently bought together with the item viewed by the customer.
... ... @@ -239,7 +239,7 @@
239 239  |(% style="width:399px" %)[[**Abandoned Cart**>>doc:Main.Usage.Smart_Communications.Campaign_list.Triggers.WebHome||anchor="H41144043E44843543D43D43044F43A43E44043743843D430"]]|(% style="width:370px" %)Product added to cart but not purchased|(% style="width:446px" %)Send an email after X days with products most frequently bought together with the items in the customer’s cart.
240 240  |(% style="width:399px" %)[[**Thank You for Your Purchase!**>>doc:Main.Usage.Smart_Communications.Campaign_list.Triggers.WebHome||anchor="H42143443543B43043D43743043A430437"]]|(% style="width:370px" %)Customer made a purchase|(% style="width:446px" %)Send an email after X days with products most frequently bought together with the items in the customer’s order.
241 241  
242 -==== 3. Use cases for the Bought Together algorithm in website personalization ====
250 +==== 3. Use Cases for the **Bought Together** Algorithm in Website Personalization ====
243 243  
244 244  (% class="table-bordered" style="width:1218px" %)
245 245  (% class="info" %)|(% style="text-align:center; width:399px" %)**Campaign**|(% style="text-align:center; width:369px" %)**Trigger**|(% style="text-align:center; width:447px" %)**Use Case**
... ... @@ -248,7 +248,7 @@
248 248  |(% style="width:399px" %)[[**Product Added to Cart**>>doc:Main.Usage.Smart_Communications.Campaign_list.Triggers.WebHome||anchor="H41443E43143043243B43543D44243E43243044043243A43E43D44243543943D435440"]]|(% style="width:369px" %)Product added to cart|(% style="width:447px" %)**Frequently Bought Together** section.
249 249  Recommend complementary products.
250 250  
251 -==== 4. General concept of the Bought Together algorithm ====
259 +==== 4. General Concept of the **Bought Together** Algorithm ====
252 252  
253 253  This algorithm incorporates a series of models and techniques based on the **[[Association Rule Learning>>https://en.wikipedia.org/wiki/Association_rule_learning]]** methodology.
254 254  
... ... @@ -283,9 +283,9 @@
283 283  * Pears to a customer who purchased Brie cheese (Rule 3).
284 284  )))
285 285  
286 -=== **{{id name="05"/}}Personalized Product Recommendations algorithm** ===
294 +=== **{{id name="05"/}}“Personalized Product Recommendations” Algorithm** ===
287 287  
288 -==== 1. Description of the Personalized Product Recommendations algorithm ====
296 +==== 1. Description of the **Personalized Product Recommendations** Algorithm ====
289 289  
290 290  (% class="wikigeneratedid" id="H" %)
291 291  The **Personalized Product Recommendations** algorithm generates product suggestions based on an individual customer’s behavior (Customer ID) and the behavior of similar customers.
... ... @@ -294,8 +294,10 @@
294 294  (% class="wikigeneratedid" %)
295 295  To predict optimal customer preferences, the machine learning model uses data on customer behavior and purchase history, online activity, customer profiles and attributes, product attributes and statistics, and other parameters.
296 296  
297 -==== 2. Use cases for the Personalized Product Recommendations algorithm in personalized campaigns ====
305 +==== 2. Use Cases for the **Personalized Product Recommendations** Algorithm in Personalized Campaigns ====
298 298  
307 +**Email Campaigns:**
308 +
299 299  (% class="table-bordered" style="width:1218px" %)
300 300  (% class="info" %)|(% style="text-align:center; width:399px" %)**Campaign**|(% style="text-align:center; width:370px" %)**Trigger**|(% style="text-align:center; width:446px" %)**Use Case**
301 301  |(% style="width:399px" %)(((
... ... @@ -308,7 +308,7 @@
308 308  |(% style="width:399px" %)**Declining Purchase Amount**|(% style="width:370px" %)Customer’s purchase amount decreased by X% over a period|(% style="width:446px" %)If purchase amount drops by X%, send an email with personalized product recommendations.
309 309  |(% style="width:399px" %)[[**Declining Website Visits**>>doc:Main.Usage.Smart_Communications.Campaign_list.Triggers.WebHome||anchor="H41F44043E44843B43E43443D43543944143F43E44143B43543443D43543343E43F43E44143544943543D43844F441430439442430"]]|(% style="width:370px" %)Customer hasn’t visited the site|(% style="width:446px" %)Send an email if the customer hasn’t visited the site in X days.
310 310  
311 -==== 3. Use cases for the Personalized Product Recommendations algorithm in website personalization ====
321 +==== 3. Use Cases for the **Personalized Product Recommendations** Algorithm in Website Personalization ====
312 312  
313 313  (% class="table-bordered" style="width:1227px" %)
314 314  (% class="info" %)|(% style="text-align:center; width:399px" %)**Campaign**|(% style="text-align:center; width:369px" %)**Trigger**|(% style="text-align:center; width:452px" %)**Use Case**
... ... @@ -317,7 +317,7 @@
317 317  |(% style="width:399px" %)[[**Website Login**>>doc:Main.Usage.Smart_Communications.Campaign_list.Triggers.WebHome||anchor="H41A43B43843543D44243F43E44143544243843B441430439442"]]|(% style="width:369px" %)Authorized customer login|(% style="width:452px" %)**You Might Like** or **Just for You** section.
318 318  Recommendations related to the viewed product.
319 319  
320 -==== 4. General concept of the Personalized Product Recommendations algorithm ====
330 +==== 4. General Concept of the **Personalized Product Recommendations** Algorithm ====
321 321  
322 322  The **Personalized Product Recommendations** algorithm is an ensemble of multiple models and algorithms. Its foundation is the [[Collaborative Filtering>>https://en.wikipedia.org/wiki/Collaborative_filtering]] technique.
323 323  Using this method within an ensemble of models—alongside other algorithms—produces more relevant product recommendations for each customer.
Recom_02.png
Size
... ... @@ -1,1 +1,1 @@
1 -26.3 KB
1 +26.5 KB
Content
Created 2025/10/22 03:38
Last edited 2026/03/25 10:03

News
Updates
Tag cloud
Glossary
Site